To see the other types of publications on this topic, follow the link: Coreference.
Journal articles on the topic 'Coreference'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Coreference.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Gilbert, Nathan. "Acquiring Domain Specific Knowledge and Coreference Cues for Coreference Resolution." Proceedings of the AAAI Conference on Artificial Intelligence 26, no. 1 (September 20, 2021): 2390–91. http://dx.doi.org/10.1609/aaai.v26i1.8190.
Full textAbstract:
Current Coreference Resolution systems utilize a broad range of general knowledge features to make resolutions in a general setting. These approaches ignore coreference knowledge found in domain specific collections and how coreferent entities interact in different domains. This research addresses these issues by developing knowledge bases of coreference characteristics drawn from annotated and unannotated domain texts and utilizing lexical and discourse information to improve resolution.
2
Žitkus, Voldemaras, Rita Butkienė, Rimantas Butleris, Rytis Maskeliūnas, Robertas Damaševičius, and Marcin Woźniak. "Minimalistic Approach to Coreference Resolution in Lithuanian Medical Records." Computational and Mathematical Methods in Medicine 2019 (March 20, 2019): 1–14. http://dx.doi.org/10.1155/2019/9079840.
Full textAbstract:
Coreference resolution is a challenging part of natural language processing (NLP) with applications in machine translation, semantic search and other information retrieval, and decision support systems. Coreference resolution requires linguistic preprocessing and rich language resources for automatically identifying and resolving such expressions. Many rarer and under-resourced languages (such as Lithuanian) lack the required language resources and tools. We present a method for coreference resolution in Lithuanian language and its application for processing e-health records from a hospital reception. Our novelty is the ability to process coreferences with minimal linguistic resources, which is important in linguistic applications for rare and endangered languages. The experimental results show that coreference resolution is applicable to the development of NLP-powered online healthcare services in Lithuania.
3
Lutfullina, G. F. "TEMPORAL COREFERENCE IN ENGLISH." Voprosy Kognitivnoy Lingvistiki, no. 2 (2024): 99–109. http://dx.doi.org/10.20916/1812-3228-2024-2-99-109.
Full textAbstract:
The article using the material of the English language focuses on studying the issues of temporal coreference. The purpose of the study is to identify the possibilities of implementing temporal coreference using Progressive forms in the English language. In verbal representing temporal reference in English, the referential moment can be expressed by Past Simple, implying a limited interval. These Tense forms may be antecedents for others. The remaining Tenses are anaphoric to it. In case of non-verbal representation of temporal reference, the adverbial modifier of pointed temporal semantics can express the referential moment. Coreference is possible in case of: 1) two non-verbally expressed time intervals, referring to one time interval: the first specifies a larger period, including the second; 2) two verbally expressed intervals; 3) one verbally expressed interval and a second, non-verbally represented. Temporal coreference is represented where a non-verbally expressed referential moment is anaphoric with a time interval verbally implied by predicates in the following Tenses: Past Progressive, Past Simple, Present Progressive, Future Simple. Present Progressive is characterized by coreference with the moment of speech or the present actual moment. Two predicates in Past Progressive and Past Simple can be coreferent to the referential moment represented by the predicate in the Past Simple. Two predicates in Present and Past Progressive can be coreferent provided they are coreferent to the moment of speech or to another moment.
4
Darchuk, Natalia. "Coreference in the poetic works of Lesia Ukrainka." Ukrainian Linguistics, no. 52 (2022): 93–115. http://dx.doi.org/10.17721/um/52(2022).93-115.
Full textAbstract:
The category of coreference plays an important role in the creation of texts, as it is based on fundamental principles of text organization. The linearity of a text and the non-linearity of a situation described in the text are closely related to the mention of elements of a situation with another nomination of this object. Therefore, chains of coreferential names appear in the text and, having a binary relation, partly cause the emergence of a secondary nomination, which is an anaphoric relation with the primary nomination. The purpose of this article is to study the category of coreference in the poetic speech of Lesia Ukrainka based on the corpus of the Ukrainian language represented on mova.info. The object of the research is the idiostyle of Lesia Ukrainka’s poetry, and the subject is the functioning of the category of coreference. The categorical essence of coreference is characterized, the types of representatives of real objects, their functional and stylistic varieties and typical objects of representation in a poetic text are determined, and the most frequent structures are considered. Software for working with coreference has been developed and implemented. It has a user-friendly interface, which allows searching, sort, and doing the quantitative processing of the collected information according to the needs of researchers. On the material of 153 texts, 1520 referentially identical pairs are established. The coreferentiality index and the index of coreference coverage of the text proposed in this article helped to quantitatively assess the saturation of the text with the category of coreference. In addition, the classification of coreferential relations is composed: 1) identity; 2) collection gap; 3) part-whole; 4) predicative identity; 5) metonymy; 6) association. A dependency tree of a sentence made it possible to determine the location of coreferential pairs in the sentence, the position relative to each other, the belonging of the segment with the coreferent or the referent to the complicators of the sentence, i.e., a subordinate clause or phrases. This representation also helped to establish the type of syntactic relationship between the coreferent and the referent, the type of syntactic-semantic relationship between them, the presence of referent-dependent words, the intersection of the coreferent and the referent in gender and number. Automatic extraction of coreferential pairs from dependency trees allowed building intersentential coreference.
5
Rahman, A., and V. Ng. "Narrowing the Modeling Gap: A Cluster-Ranking Approach to Coreference Resolution." Journal of Artificial Intelligence Research 40 (February 25, 2011): 469–521. http://dx.doi.org/10.1613/jair.3120.
Full textAbstract:
Traditional learning-based coreference resolvers operate by training the mention-pair model for determining whether two mentions are coreferent or not. Though conceptually simple and easy to understand, the mention-pair model is linguistically rather unappealing and lags far behind the heuristic-based coreference models proposed in the pre-statistical NLP era in terms of sophistication. Two independent lines of recent research have attempted to improve the mention-pair model, one by acquiring the mention-ranking model to rank preceding mentions for a given anaphor, and the other by training the entity-mention model to determine whether a preceding cluster is coreferent with a given mention. We propose a cluster-ranking approach to coreference resolution, which combines the strengths of the mention-ranking model and the entity-mention model, and is therefore theoretically more appealing than both of these models. In addition, we seek to improve cluster rankers via two extensions: (1) lexicalization and (2) incorporating knowledge of anaphoricity by jointly modeling anaphoricity determination and coreference resolution. Experimental results on the ACE data sets demonstrate the superior performance of cluster rankers to competing approaches as well as the effectiveness of our two extensions.
6
De Marneffe, Marie-Catherine, Marta Recasens, and Christopher Potts. "Modeling the Lifespan of Discourse Entities with Application to Coreference Resolution." Journal of Artificial Intelligence Research 52 (March 31, 2015): 445–75. http://dx.doi.org/10.1613/jair.4565.
Full textAbstract:
A discourse typically involves numerous entities, but few are mentioned more than once. Distinguishing those that die out after just one mention (singleton) from those that lead longer lives (coreferent) would dramatically simplify the hypothesis space for coreference resolution models, leading to increased performance. To realize these gains, we build a classifier for predicting the singleton/coreferent distinction. The models feature representations synthesize linguistic insights about the factors affecting discourse entity lifespans (especially negation, modality, and attitude predication) with existing results about the benefits of surface (part-of-speech and n-gram-based) features for coreference resolution. The model is effective in its own right, and the feature representations help to identify the anchor phrases in bridging anaphora as well. Furthermore, incorporating the model into two very different state-of-the-art coreference resolution systems, one rule-based and the other learning-based, yields significant performance improvements.
7
Balaji, J., T. V. Geetha, and P. Ranjani. "Graph-Based Bootstrapping for Coreference Resolution." Journal of Intelligent Systems 23, no. 3 (September 1, 2014): 293–310. http://dx.doi.org/10.1515/jisys-2013-0056.
Full textAbstract:
AbstractCoreference resolution is a challenging natural language processing task, and it is difficult to identify the correct mentions of an entity that can be any noun or noun phrase. In this article, a semisupervised, two-stage pattern-based bootstrapping approach is proposed for the coreference resolution task. During Stage 1, the possible mentions are identified using word-based features, and during Stage 2, the correct mentions are identified by filtering the non-coreferents of an entity using statistical measures and graph-based features. Whereas the existing approaches use morphosyntactic and number/gender agreement features, the proposed approach uses semantic graph-based context-level semantics and nested noun phrases in the correct mentions identification. Moreover, mentions without the number/gender information are identified, using the context-based features of the semantic graph. The evaluation performed for the coreference resolution shows significant improvements, when compared with the word association-based bootstrapping systems.
8
POGORILYY, S. D., and P. V. BILETSKY. "USAGE OF A GRAPHICS PROCESSOR TO ACCELERATE COREFERENCE RESOLUTION WHILE USING THE RoBERTa MODEL." Scientific papers of Donetsk National Technical University. Series: Informatics, Cybernetics and Computer Science 2 - №1, no. 33-34 (2022): 4–9. http://dx.doi.org/10.31474/1996-1588-2021-2-33-4-9.
Full textAbstract:
"The problem of finding coreferential objects (coreference resolution) in Ukrainian-language texts is considered, examples of co-referentiality in the Ukrainian language are given. Coreference in texts means the relationship between syntactic units that point to the same object (referent) in a given context. The differences between English-language and Ukrainian-language texts in solving the problem of searching for coreferenced objects and the difficulties that arise in finding coreferenced objects are noted. In particular, there are differences in the order of words in sentences: strict word order in English and arbitrary word order in Ukrainian. It is also pointed out the need to take into account the relationship between objects that are not part of the co-reference groups (predicates and secondary parts of sentence). Created an application that searches for reference objects in Ukrainian-language texts using the Transformers library and the RoBERTa language model. The use of a graphics processor to speed up the search for referential objects by the algorithm is considered. The work of the algorithm was tested on a set containing 2500 texts. 21.3 times acceleration reached due to the use of a graphics processor (GPU) in comparison to the performance of CPU. The resulting acceleration has greatly facilitated the development and testing of the application."
9
Lu, Jing, and Vincent Ng. "Span-Based Event Coreference Resolution." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 15 (May 18, 2021): 13489–97. http://dx.doi.org/10.1609/aaai.v35i15.17591.
Full textAbstract:
Motivated by the recent successful application of span-based models to entity-based information extraction tasks, we investigate span-based models for event coreference resolution, focusing on determining (1) whether the successes of span-based models of entity coreference can be extended to event coreference; (2) whether exploiting the dependency between event coreference and the related subtask of trigger detection; and (3) whether automatically computed entity coreference information can benefit span-based event coreference resolution. Empirical results on the standard evaluation dataset provide affirmative answers to all three questions.
10
RECASENS, M., and E. HOVY. "BLANC: Implementing the Rand index for coreference evaluation." Natural Language Engineering 17, no. 4 (December 6, 2010): 485–510. http://dx.doi.org/10.1017/s135132491000029x.
Full textAbstract:
AbstractThis paper addresses the current state of coreference resolution evaluation, in which different measures (notably, MUC, B3, CEAF, and ACE-value) are applied in different studies. None of them is fully adequate, and their measures are not commensurate. We enumerate the desiderata for a coreference scoring measure, discuss the strong and weak points of the existing measures, and propose the BiLateral Assessment of Noun-Phrase Coreference, a variation of the Rand index created to suit the coreference task. The BiLateral Assessment of Noun-Phrase Coreference rewards both coreference and non-coreference links by averaging the F-scores of the two types, does not ignore singletons – the main problem with the MUC score – and does not inflate the score in their presence – a problem with the B3 and CEAF scores. In addition, its fine granularity is consistent over the whole range of scores and affords better discrimination between systems.
11
Wind Cowles, H. "influence of 'aboutness' on pronominal coreference." ZAS Papers in Linguistics 48 (January 1, 2007): 23–38. http://dx.doi.org/10.21248/zaspil.48.2007.352.
Full textAbstract:
Previous work examining the role of antecedent accessibility in pronominal coreference has often linked coreference to prominent structural positions that in turn are linked to information structure statuses such as topic. Three experiments examine the influence of topichood independently of structural prominence by exploring the influence of the pragmatic notion of aboutness on the written production of pronominal coreferring expressions. The results show that being mentioned in an about-phrase increases the likelihood that a referent will be selected as the future topic of a following sentence as well as increasing the proportion of responses with early, pronominal coreference to that referent, at the expense of coreference with the subject. These results suggest that coreference is sensitive to the status of other, structurally non-prominent referents in discourse, and that the pragmatic notion of aboutness influences pronominal coreference.
12
Aldawsari, Mohammed, Manjur Kolhar, and Omer Salih Dawood Omer. "Within-Document Arabic Event Coreference: Challenges, Datasets, Approaches and Future Direction." Applied Sciences 13, no. 19 (October 6, 2023): 11004. http://dx.doi.org/10.3390/app131911004.
Full textAbstract:
Event coreference resolution is a crucial component in Natural Language Processing (NLP) applications as it directly affects text summarization, machine translation, classification, and textual entailment. However, the research on this task for Arabic language is limited, compared to other languages such as English, Chinese and Spanish. This paper aims to review the state-of-the-art approaches in event coreference (EC) within the context of coreference resolution tasks, emphasizing the significance of EC in NLP. The focus is placed on the latest developments in Arabic language processing related to event coreference. To fill this gap, a comprehensive study of existing work is conducted, and new approaches are suggested. The paper highlights the challenges specific to Arabic event coreference resolution, such as the variability of verb forms, pronoun ambiguity, ellipsis and null arguments, lexical and morphological variation, lack of annotated resources, discourse and pragmatic context, and cultural and contextual sensitivity. Addressing these challenges requires a deep understanding of Arabic linguistics, advanced NLP techniques, and the availability of annotated resources. Furthermore, this paper examines the existing datasets and methods for Arabic event coreference and proposes an annotation scheme. By leveraging existing NLP algorithms and developing event coreference resolution systems tailored for Arabic, the accuracy and performance of NLP tasks can be significantly improved.
13
Nilsson Björkenstam, Kristina. "SUC-CORE: A Balanced Corpus Annotated with Noun Phrase Coreference." Northern European Journal of Language Technology 3 (September 16, 2013): 19–39. http://dx.doi.org/10.3384/nejlt.2000-1533.1332.
Full textAbstract:
This paper describes SUC-CORE, a subset of the Stockholm Ume°a Corpus and the Swedish Treebank annotated with noun phrase coreference. While most coreference annotated corpora consist of exts of similar types within related domains, SUC-CORE consists of both informative and imaginative prose and covers a wide range of literary genres and domains. This allows for exploration of coreference cross different text types, but it also means that there are limited amounts of data within each type. Future work on coreference resolution for Swedish should include making more annotated data vailable for the research community.
14
Kübler, Sandra, and Desislava Zhekova. "Multilingual coreference resolution." Language and Linguistics Compass 10, no. 11 (November 2016): 614–31. http://dx.doi.org/10.1111/lnc3.12208.
Full text
15
Ángel Pinillos, N. "Coreference and meaning." Philosophical Studies 154, no. 2 (April 4, 2010): 301–24. http://dx.doi.org/10.1007/s11098-010-9543-y.
Full text
16
LAWLOR, KRISTA. "Varieties of Coreference." Philosophy and Phenomenological Research 81, no. 2 (September 2010): 485–95. http://dx.doi.org/10.1111/j.1933-1592.2010.00406.x.
Full text
17
Deemter, Kees van, and Rodger Kibble. "On Coreferring: Coreference in MUC and Related Annotation Schemes." Computational Linguistics 26, no. 4 (December 2000): 629–37. http://dx.doi.org/10.1162/089120100750105966.
Full textAbstract:
In this paper, it is argued that “coreference” annotations, as performed in the MUC community for example, go well beyond annotation of the relation of coreference proper. As a result, it is not always clear what semantic relation these annotations are encoding. The paper discusses a number of problems with these annotations and concludes that rethinking of the coreference task is needed before the task is expanded. In particular, it suggests a division of labor whereby annotation of the coreference relation proper is separated from other tasks such as annotation of bound anaphora and of the relation between a subject and a predicative NP.
18
Yang, Bishan, Claire Cardie, and Peter Frazier. "A Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolution." Transactions of the Association for Computational Linguistics 3 (December 2015): 517–28. http://dx.doi.org/10.1162/tacl_a_00155.
Full textAbstract:
We present a novel hierarchical distance-dependent Bayesian model for event coreference resolution. While existing generative models for event coreference resolution are completely unsupervised, our model allows for the incorporation of pairwise distances between event mentions — information that is widely used in supervised coreference models to guide the generative clustering processing for better event clustering both within and across documents. We model the distances between event mentions using a feature-rich learnable distance function and encode them as Bayesian priors for nonparametric clustering. Experiments on the ECB+ corpus show that our model outperforms state-of-the-art methods for both within- and cross-document event coreference resolution.
19
Kunz, Kerstin. "A method for investigating coreference in translations and originals." Languages in Contrast 7, no. 2 (December 7, 2007): 267–87. http://dx.doi.org/10.1075/lic.7.2.10kun.
Full textAbstract:
Coreference is one essential strategy of coherence and cohesion as it establishes connectivity in texts. This connection is evoked by linguistic devices on the text surface but has to be interpreted mentally as a relation between extralinguistic referents. Since translators are concerned with the reception of connectivity in source texts and the production of the same kind of connectivity in target texts coreference is an important process taking place in translation. The present paper deals with the elaboration of a method for investigating nominal coreference in originals and translations. In order to build parameters for the empirical analysis of coreference in English and German corpora we provide an overview over various mechanisms affecting the creation of coreference relations in source and target texts. We take account of linguistic as well as extralinguistic aspects as interdependent and interacting factors potentially causing shifts in coreference. The model we establish on the basis of these considerations allows us to investigate nominal coreferring expressions as well as analyse the relation of reference identity created between these expressions. Hence, our model facilitates exhaustive research on a very fine-grained scale. It allows us to capture differences on the lexicogrammatical as well as on a semantic and conceptual level and, thus, paves the way for interpretation on a more conceptual level.
20
Kopeć, Mateusz. "Three-step coreference-based summarizer for Polish news texts." Poznan Studies in Contemporary Linguistics 55, no. 2 (June 26, 2019): 397–443. http://dx.doi.org/10.1515/psicl-2019-0015.
Full textAbstract:
Abstract This article addresses the problem of automatic summarization of press articles in Polish. The main novelty of this research lays in the proposal of a three-step summarization algorithm which benefits from using coreference information. In related work section, all coreference-based approaches to summarization are presented. Then we describe in detail all publicly available summarization tools developed for Polish language. We state the problem of single-document press article summarization for Polish, describing the training and evaluation dataset: the POLISH SUMMARIES CORPUS. Next, a new coreference-based extractive summarization system NICOLAS is introduced. Its algorithm utilises advanced third-party preprocessing tools to extract the coreference information from the text to be summarized. This information is transformed into a complex set of features related to coreference concepts (mentions and coreference clusters) that are used for training the summarization system (on the basis of a manually prepared gold summaries corpus). The proposed solution is compared to the best publicly available summarization systems for Polish language and two state-of-the-art tools, developed for English language, but adapted to Polish for this article. NICOLAS summarization system obtains best scores, for selected metrics outperforming other systems in a statistically significant way. The evaluation also contains calculation of interesting upper-bounds: human performance and theoretical upper-bound.
21
Li, Yufei, Xiaoyong Ma, Xiangyu Zhou, Pengzhen Cheng, Kai He, and Chen Li. "Knowledge enhanced LSTM for coreference resolution on biomedical texts." Bioinformatics 37, no. 17 (March 11, 2021): 2699–705. http://dx.doi.org/10.1093/bioinformatics/btab153.
Full textAbstract:
Abstract Motivation Bio-entity Coreference Resolution focuses on identifying the coreferential links in biomedical texts, which is crucial to complete bio-events’ attributes and interconnect events into bio-networks. Previously, as one of the most powerful tools, deep neural network-based general domain systems are applied to the biomedical domain with domain-specific information integration. However, such methods may raise much noise due to its insufficiency of combining context and complex domain-specific information. Results In this article, we explore how to leverage the external knowledge base in a fine-grained way to better resolve coreference by introducing a knowledge-enhanced Long Short Term Memory network (LSTM), which is more flexible to encode the knowledge information inside the LSTM. Moreover, we further propose a knowledge attention module to extract informative knowledge effectively based on contexts. The experimental results on the BioNLP and CRAFT datasets achieve state-of-the-art performance, with a gain of 7.5 F1 on BioNLP and 10.6 F1 on CRAFT. Additional experiments also demonstrate superior performance on the cross-sentence coreferences. Availability and implementation The source code will be made available at https://github.com/zxy951005/KB-CR upon publication. Data is avaliable at http://2011.bionlp-st.org/ and https://github.com/UCDenver-ccp/CRAFT/releases/tag/v3.1.3. Supplementary information Supplementary data are available at Bioinformatics online.
22
DEMİR, Şeniz. "Neural Coreference Resolution for Turkish." Journal of Intelligent Systems: Theory and Applications 6, no. 1 (March 15, 2023): 85–95. http://dx.doi.org/10.38016/jista.1225097.
Full textAbstract:
Coreference resolution deals with resolving mentions of the same underlying entity in a given text. This challenging task is an indispensable aspect of text understanding and has important applications in various language processing systems such as question answering and machine translation. Although a significant amount of studies is devoted to coreference resolution, the research on Turkish is scarce and mostly limited to pronoun resolution. To our best knowledge, this article presents the first neural Turkish coreference resolution study where two learning-based models are explored. Both models follow the mention-ranking approach while forming clusters of mentions. The first model uses a set of hand-crafted features whereas the second coreference model relies on embeddings learned from large-scale pre-trained language models for capturing similarities between a mention and its candidate antecedents. Several language models trained specifically for Turkish are used to obtain mention representations and their effectiveness is compared in conducted experiments using automatic metrics. We argue that the results of this study shed light on the possible contributions of neural architectures to Turkish coreference resolution.
23
Šteflovič, Kirsten, and Jozef Kapusta. "Coreference Resolution for Improving Performance Measures of Classification Tasks." Applied Sciences 13, no. 16 (August 15, 2023): 9272. http://dx.doi.org/10.3390/app13169272.
Full textAbstract:
There are several possibilities to improve classification in natural language processing tasks. In this article, we focused on the issue of coreference resolution that was applied to a manually annotated dataset of true and fake news. This dataset was used for the classification task of fake news detection. The research aimed to determine whether performing coreference resolution on the input data before classification or classifying them without performing coreference resolution is more effective. We also wanted to verify whether it is possible to enhance classifier performance metrics by incorporating coreference resolution into the data preparation process. A methodology was proposed, in which we described the implementation methods in detail, starting from the identification of entity mentions in the text using the neuralcoref algorithm, then through word-embedding models (TF–IDF, Doc2Vec), and finally to several machine learning methods. The result was a comparison of the implemented classifiers based on the performance metrics described in the theoretical part. The best result for accuracy was observed for the dataset with coreference resolution applied, which had a median value of 0.8149, while for the F1 score, the best result had a median value of 0.8101. However, the more important finding is that the processed data with the application of coreference resolution led to an improvement in performance metrics in the classification tasks.
24
Durrett, Greg, and Dan Klein. "A Joint Model for Entity Analysis: Coreference, Typing, and Linking." Transactions of the Association for Computational Linguistics 2 (December 2014): 477–90. http://dx.doi.org/10.1162/tacl_a_00197.
Full textAbstract:
We present a joint model of three core tasks in the entity analysis stack: coreference resolution (within-document clustering), named entity recognition (coarse semantic typing), and entity linking (matching to Wikipedia entities). Our model is formally a structured conditional random field. Unary factors encode local features from strong baselines for each task. We then add binary and ternary factors to capture cross-task interactions, such as the constraint that coreferent mentions have the same semantic type. On the ACE 2005 and OntoNotes datasets, we achieve state-of-the-art results for all three tasks. Moreover, joint modeling improves performance on each task over strong independent baselines.
25
Muhhasin, Mohammad, and Dewi Ayu Hidayati. "Coreferential Devices in the Quranic Interpretation." English Education: Jurnal Tadris Bahasa Inggris 12, no. 1 (July 5, 2019): 97–119. http://dx.doi.org/10.24042/ee-jtbi.v12i1.4431.
Full textAbstract:
This article mainly discusses the coreference in the Quranic interpretation of Surah Albaqarah by Abdullah Yusuf Ali. The aims of the research are: to describe and explain the coreference types found in the Quranic interpretation, the coreference devices, and relationship types of the coreferential devices. The is a kind of descriptive qualitative research. The population consisted 286 interpretation texts of Surah Al-Baqarah with 112 samples taken as the data of the research chosen by using purposive sampling technique. The result of the research shows that the coreference types found in the Quranic interpretation are: repetition (6,55%), lexical change (18,03%), substitution (50,81%) and ellipsis (24,59%). Meanwhile, the coreferential devices found are: repetition, lexical change, and substitution. Finally, the relationship types of the co-referential devices are anaphoric (88,52%) and cataphoric (11,48%)
26
Bevacqua, Luca, Sharid Loáiciga, Hannah Rohde, and Christian Hardmeier. "Event and Entity Coreference Across Five Languages: Effects of Context and Referring Expression." Dialogue & Discourse 12, no. 2 (December 18, 2021): 192–226. http://dx.doi.org/10.5210/dad.2021.207.
Full textAbstract:
Current work on coreference focuses primarily on entities, often leaving unanalysed the use of anaphors to corefer with antecedents such as events and textual segments. Moreover, the anaphoric forms that speakers use for entity and non-entity coreference are not mutually exclusive. This ambiguity has been the subject of recent work in English, with evidence of a split between comprehenders' preferential interpretation of personal versus demonstrative pronouns. In addition, comprehenders are shown to be sensitive to antecedent complexity and aspectual status, two verb-driven cues that signal how an event is being portrayed. Here we extend this work via a comparison across five languages (English, French, German, Italian, and Spanish). With a story-continuation experiment, we test how different referring expressions corefer with entity and event antecedents and whether verbal features such as argument structure and aspect influence this choice. Our results show widely consistent, not categorical biases across languages: entity coreference is favoured for personal pronouns and event coreference for demonstratives. Antecedent complexity increases the rate at which anaphors are taken to corefer with an event antecedent, but portraying an event as completed does not reach statistical significance (though showing quite uniform patterns). Lastly, we report a comparison of the same referring expressions to refer to entity and event antecedents in a trilingual parallel corpus annotated with coreference.Together, the results provide a first crosslingual picture of coreference preferences beyond the restricted entity-only patterns targeted by most existing work on coreference. The five languages are all shown to allow gradable use of pronouns for entity and event coreference, with biases that align with existing generalizations about the link between prominence and the use of reduced referring expressions. The studies also show the feasibility of manipulating targeted verb-driven cues across multiple languages to support crosslingual comparisons.
27
Martschat, Sebastian, and Michael Strube. "Latent Structures for Coreference Resolution." Transactions of the Association for Computational Linguistics 3 (December 2015): 405–18. http://dx.doi.org/10.1162/tacl_a_00147.
Full textAbstract:
Machine learning approaches to coreference resolution vary greatly in the modeling of the problem: while early approaches operated on the mention pair level, current research focuses on ranking architectures and antecedent trees. We propose a unified representation of different approaches to coreference resolution in terms of the structure they operate on. We represent several coreference resolution approaches proposed in the literature in our framework and evaluate their performance. Finally, we conduct a systematic analysis of the output of these approaches, highlighting differences and similarities.
28
Soon, Wee Meng, Hwee Tou Ng, and Daniel Chung Yong Lim. "A Machine Learning Approach to Coreference Resolution of Noun Phrases." Computational Linguistics 27, no. 4 (December 2001): 521–44. http://dx.doi.org/10.1162/089120101753342653.
Full textAbstract:
In this paper, we present a learning approach to coreference resolution of noun phrases in unrestricted text. The approach learns from a small, annotated corpus and the task includes resolving not just a certain type of noun phrase (e.g., pronouns) but rather general noun phrases. It also does not restrict the entity types of the noun phrases; that is, coreference is assigned whether they are of “organization,” “person,” or other types. We evaluate our approach on common data sets (namely, the MUC-6 and MUC-7 coreference corpora) and obtain encouraging results, indicating that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches. Our system is the first learning-based system that offers performance comparable to that of state-of-the-art nonlearning systems on these data sets.
29
Zhukovska, V. ""Absoluteness" of the Absolute Construction in Present-Day English: a Corpus-Based Analysis." Вісник Житомирського державного університету імені Івана Франка. Філологічні науки, no. 1(87) (May 13, 2018): 74–79. http://dx.doi.org/10.35433/philology.1(87).2018.74-79.
Full textAbstract:
The article focuses on the question of presence / absence of referential relations (coreference) between the unaugmented absolute construction and its matrix clause in Present-day English. Based on a representative sample from the corpus of the English language BYU-BNC, the traditional approach to the absolute construction as an "independent" structure that has no connection with the rest of the sentence is reconsidered. The analysis of referential relations between the unaugmented absolute construction and its matrix clause has established that cases of coreference (full and partial) significantly outweigh the cases of absence of coreference. These findings indicate that the construction is semantically / logically related to its matrix clause. Furthermore, the obtained data show that meronimic (part-whole) relations prevail in the analysed sample. More precisely, the relations of the types "component - integral object" and "member - collection" are the most numerous. The obtained results suggest that in Present-day English unaugmented absolute constructions compensate lack of syntactic connection with the matrix clause with closer semantic relations, explicitly expressed by complete or partial coreference. In our further research on the issue we intend to carry out a similar analysis for the English augmented absolute constructions in order to determine prevailing types of coreference between them and the matrix clause.
30
Zhang, Zhuowei, Mengting Hu, Yinhao Bai, and Zhen Zhang. "Coreference Graph Guidance for Mind-Map Generation." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 17 (March 24, 2024): 19623–31. http://dx.doi.org/10.1609/aaai.v38i17.29935.
Full textAbstract:
Mind-map generation aims to process a document into a hierarchical structure to show its central idea and branches. Such a manner is more conducive to understanding the logic and semantics of the document than plain text. Recently, a state-of-the-art method encodes the sentences of a document sequentially and converts them to a relation graph via sequence-to-graph. Though this method is efficient to generate mind-maps in parallel, its mechanism focuses more on sequential features while hardly capturing structural information. Moreover, it's difficult to model long-range semantic relations. In this work, we propose a coreference-guided mind-map generation network (CMGN) to incorporate external structure knowledge. Specifically, we construct a coreference graph based on the coreference semantic relationship to introduce the graph structure information. Then we employ a coreference graph encoder to mine the potential governing relations between sentences. In order to exclude noise and better utilize the information of the coreference graph, we adopt a graph enhancement module in a contrastive learning manner. Experimental results demonstrate that our model outperforms all the existing methods. The case study further proves that our model can more accurately and concisely reveal the structure and semantics of a document. Code and data are available at https://github.com/Cyno2232/CMGN.
31
Hsu, Jennifer Ryan, Helen Smith Cairns, Sarita Eisenberg, and Gloria Schlisselberg. "When do children avoid backwards coreference?" Journal of Child Language 18, no. 2 (June 1991): 339–53. http://dx.doi.org/10.1017/s0305000900011090.
Full textAbstract:
ABSTRACTThis study investigated the claim that very young children avoid backwards coreference in their interpretation of sentences containing pronouns. Eighty-one children ranging in age from 3;1 to 8;0 and eight adults acted out four types of pronominal sentences. Cross-sectional data and individual response patterns reveal that children initially, prefer internal coreference even when such a response is disallowed for structural reasons. Avoidance of backwards coreference appears to be a late developing phenomenon characteristic of six-year-olds. Adult response patterns, which are manifested by some very young children, emerge as the dominant pattern by age seven.
32
Pogorilyy, S. D., and P. V. Biletskyi. "Coreference resolution algorithm for Ukrainian-language texts using decision trees." PROBLEMS IN PROGRAMMING, no. 3-4 (December 2022): 85–91. http://dx.doi.org/10.15407/pp2022.03-04.085.
Full textAbstract:
The paper examines the problem of coreference resolution in Ukrainian-language texts using decision trees. An application that uses vector representations of Elmo words and other characteristics for the automated formation of a decision tree has been developed. A set of prepared texts containing more than 360,000 words was used to form the decision tree and evaluate the accuracy of the algorithm. The decision tree created to determine whether a pair of objects is coreference was used to form clusters of coreference objects. Special metrics were used for comparison with the results obtained by other algorithms in the Ukrainian language.
33
Shengwei, Tian, Li Dongbai, Yu Long, Feng Guanjun, Zhao Jianguo, and Li Pu. "Anaphoricity Determination of Anaphora Resolution in Uygur Pronoun Based on CNN-LSTM Model." International Journal of Computational Intelligence and Applications 16, no. 03 (September 2017): 1750016. http://dx.doi.org/10.1142/s146902681750016x.
Full textAbstract:
As a core subtask in anaphora resolution, anaphoricity determination has aroused the interest of researchers. However, in recent work, the influence caused by the deep semantic information and the context of the coreference elements have not been taken into account. In this paper, by combining the semantic feature of Uygur, we established a Convolutional Neural Network & Long Short-Term Memory (CNN_LSTM) model in determining the anaphoricity of Uygur pronoun. Firstly, the deep negative semantic feature representation is extracted via word2vec. Secondly, the shallow explicit feature representation of coreference elements is extracted by our system. Afterwards, two kinds of features are combined to recognize whether coreference element is referential or not. The results showed that the method we used can distinguish coreference element accurately, the ACC[Formula: see text] score is 90.18% and the ACC[Formula: see text] score is 89.93%, which are higher than ANN (Artificial Neural Network) and SVM (Support Vector Machine) respectively.
34
Su, Yi-Ching, Antonella Sorace, Yuki Hirose, Keiko Mochizuki, Makiko Hirakawa, and Mineharu Nakayama. "Microvariation in L2 acquisition of backward anaphora: Mandarin versus Japanese." Journal of Japanese Linguistics 40, no. 2 (November 1, 2024): 181–207. http://dx.doi.org/10.1515/jjl-2024-2014.
Full textAbstract:
Abstract There are crosslinguistic variations for backward anaphora coreference readings although the languages, such as English, Italian, Russian, and Mandarin, that have been experimentally studied are constrained by Principle C. English allows backward anaphora coreference readings between the pronoun and the antecedent NP for sentences like “While he was dancing, Kermit ate the pizza”, but languages like Russian, Mandarin, and Japanese prohibit the coreference readings for some types of temporal subordinate clauses. In addition to the macrovariation between the English type of languages versus the Russian/Mandarin/Japanese type of languages, a microvariation exists between Mandarin and Japanese. Due to idiosyncratic constraints in Mandarin, the acceptance rate for the coreference reading in sentences with the ‘because’ clause was substantially lower in Mandarin than in Japanese. In this study, we report findings from an experiment on bi-directional L2 acquisition of backward anaphora between Mandarin and Japanese which demonstrate similar mechanisms underlying both macrovariation and microvariation for pronoun resolution of backward anaphora sentences.
35
Kehler, A., L. Kertz, H. Rohde, and J. L. Elman. "Coherence and Coreference Revisited." Journal of Semantics 25, no. 1 (September 12, 2007): 1–44. http://dx.doi.org/10.1093/jos/ffm018.
Full text
36
Halmari, Helena. "On Accessibility and Coreference." Nordic Journal of Linguistics 17, no. 1 (June 1994): 35–59. http://dx.doi.org/10.1017/s0332586500000044.
Full textAbstract:
Anaphors and the grammatical roles of their antecedents are examined in Finnish language data in order to establish a correlation between two universal hierarchies: the Keenan & Comrie (1977) NP Accessibility Hierarchy and the hierarchy of accessibility of referential expressions (Accessibility Marking Scale) (Ariel 1985, 1988, 1990). A more or less clear correlation pattern between the type of anaphoric NPs and the grammatical roles of their antecedents arises in Finnish intuition data (Section 2), and this pattern is corroborated by the data from prose text counts (Section 3). Even though a one-to-one mapping between the two hierarchies remains an idealization, it is clear that grammatical relations do bear on the type of anaphoric expression employed.
37
Mohri, Mehryar. "La Coreference et L'aspect." Lingvisticæ Investigationes. International Journal of Linguistics and Language Resources 14, no. 2 (January 1, 1990): 403–12. http://dx.doi.org/10.1075/li.14.2.10meh.
Full textAbstract:
COREFERENCE AND ASPECT We present some of the complex non-local dependencies between the elements of sentences in French, and especially their effect on coreference. Some of the parameters involved in these aspectual dependencies are listed and analysed. We then show that a more precise analysis including a simultaneous study of noun and verbal phrases is required.
38
Recasens, Marta, and Marta Vila. "On Paraphrase and Coreference." Computational Linguistics 36, no. 4 (December 2010): 639–47. http://dx.doi.org/10.1162/coli_a_00014.
Full textAbstract:
By providing a better understanding of paraphrase and coreference in terms of similarities and differences in their linguistic nature, this article delimits what the focus of paraphrase extraction and coreference resolution tasks should be, and to what extent they can help each other. We argue for the relevance of this discussion to Natural Language Processing.
39
Bejan, Cosmin, and Sanda Harabagiu. "Unsupervised Event Coreference Resolution." Computational Linguistics 40, no. 2 (June 2014): 311–47. http://dx.doi.org/10.1162/coli_a_00174.
Full textAbstract:
The task of event coreference resolution plays a critical role in many natural language processing applications such as information extraction, question answering, and topic detection and tracking. In this article, we describe a new class of unsupervised, nonparametric Bayesian models with the purpose of probabilistically inferring coreference clusters of event mentions from a collection of unlabeled documents. In order to infer these clusters, we automatically extract various lexical, syntactic, and semantic features for each event mention from the document collection. Extracting a rich set of features for each event mention allows us to cast event coreference resolution as the task of grouping together the mentions that share the same features (they have the same participating entities, share the same location, happen at the same time, etc.). Some of the most important challenges posed by the resolution of event coreference in an unsupervised way stem from (a) the choice of representing event mentions through a rich set of features and (b) the ability of modeling events described both within the same document and across multiple documents. Our first unsupervised model that addresses these challenges is a generalization of the hierarchical Dirichlet process. This new extension presents the hierarchical Dirichlet process's ability to capture the uncertainty regarding the number of clustering components and, additionally, takes into account any finite number of features associated with each event mention. Furthermore, to overcome some of the limitations of this extension, we devised a new hybrid model, which combines an infinite latent class model with a discrete time series model. The main advantage of this hybrid model stands in its capability to automatically infer the number of features associated with each event mention from data and, at the same time, to perform an automatic selection of the most informative features for the task of event coreference. The evaluation performed for solving both within- and cross-document event coreference shows significant improvements of these models when compared against two baselines for this task.
40
Zhukovska, Viktoriia. "REFERENTIAL PROPERTIES OF ENGLISH DETACHED NONFINITE CONSTRUCTIONS WITH AN EXPLICIT SUBJECT: OPERATIONALIZATION AND QUANTIFICATION." Scientific Journal of Polonia University 48, no. 5 (January 17, 2022): 94–102. http://dx.doi.org/10.23856/4812.
Full textAbstract:
This article presents the results of quantitative-corpus parameterization of reference properties of English detached nonfinite constructions with an explicit subject, carried out from the perspective of the cognitive-quantitative approach to language study. Through the prism of cognitive-constructive grammar, the syntactic patterns under scrutiny are recognized as grammatical constructions, i.e. complex semiotic units, non-compositional cognitively motivated pairings of form and conceptual meaning/ function, stored as holistic, conceptually connected, and interacting structures. Corpus-quantitative parameterization of referential properties of the given constructions presupposes the analysis of the linguistic means of expressing coreference between five micro-constructions and a corresponding matrix clause, reflected by the factors “Coreference” (COREF) and “Absence of coreference” (ØCOREF) of the parameter “Reference relations” (REFREL). Quantitative verification of the data involves a three-stage quantitative procedure incorporating 1) a multivariate analysis of variance (MANOVA), 2) a one-way analysis of variance (ANOVA), and 3) Tukey’s multiple comparison test performed with a computer statistical data analysis software R. The obtained results prove that the non-augmented constructions show a stronger semantic integration into a matrix clause, compensating lack of syntactic connection by closer reference relations, manifested by explicitly expressed full or partial coreference. The use of augmentors facilitates the identification of with-, without-, despite- and what_with- augmented constructions as syntactic patterns, thus balancing the absence of coreference and ensuring adequate cognitive processing of constructions.
41
Klemen, Matej, and Slavko Zitnik. "Neural coreference resolution for Slovene language." Computer Science and Information Systems, no. 00 (2021): 60. http://dx.doi.org/10.2298/csis201120060k.
Full textAbstract:
Coreference resolution systems aim to recognize and cluster together mentions of the same underlying entity. While there exist large amounts of research on broadly spoken languages such as English and Chinese, research on coreference in other languages is comparably scarce. In this work we first present SentiCoref 1.0 - a coreference resolution dataset for Slovene language that is comparable to English-based corpora. Further, we conduct a series of analyses using various complex models that range from simple linear models to current state-of-the-art deep neural coreference approaches leveraging pre-trained contextual embeddings. Apart from SentiCoref, we evaluate models also on a smaller coref149 Slovene dataset to justify the creation of a new corpus. We investigate robustness of the models using cross-domain data and data augmentations. Models using contextual embeddings achieve the best results - up to 0.92 average F1 score for the SentiCoref dataset. Cross-domain experiments indicate that SentiCoref allows the models to learn more general patterns, which enables them to outperform models, learned on coref149 only.
42
Lee, Heeyoung, Angel Chang, Yves Peirsman, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. "Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules." Computational Linguistics 39, no. 4 (December 2013): 885–916. http://dx.doi.org/10.1162/coli_a_00152.
Full textAbstract:
We propose a new deterministic approach to coreference resolution that combines the global information and precise features of modern machine-learning models with the transparency and modularity of deterministic, rule-based systems. Our sieve architecture applies a battery of deterministic coreference models one at a time from highest to lowest precision, where each model builds on the previous model's cluster output. The two stages of our sieve-based architecture, a mention detection stage that heavily favors recall, followed by coreference sieves that are precision-oriented, offer a powerful way to achieve both high precision and high recall. Further, our approach makes use of global information through an entity-centric model that encourages the sharing of features across all mentions that point to the same real-world entity. Despite its simplicity, our approach gives state-of-the-art performance on several corpora and genres, and has also been incorporated into hybrid state-of-the-art coreference systems for Chinese and Arabic. Our system thus offers a new paradigm for combining knowledge in rule-based systems that has implications throughout computational linguistics.
43
Bohnet, Bernd, Chris Alberti, and Michael Collins. "Coreference Resolution through a seq2seq Transition-Based System." Transactions of the Association for Computational Linguistics 11 (2023): 212–26. http://dx.doi.org/10.1162/tacl_a_00543.
Full textAbstract:
Abstract Most recent coreference resolution systems use search algorithms over possible spans to identify mentions and resolve coreference. We instead present a coreference resolution system that uses a text-to-text (seq2seq) paradigm to predict mentions and links jointly. We implement the coreference system as a transition system and use multilingual T5 as an underlying language model. We obtain state-of-the-art accuracy on the CoNLL-2012 datasets with 83.3 F1-score for English (a 2.3 higher F1-score than previous work [Dobrovolskii, 2021]) using only CoNLL data for training, 68.5 F1-score for Arabic (+4.1 higher than previous work), and 74.3 F1-score for Chinese (+5.3). In addition we use the SemEval-2010 data sets for experiments in the zero-shot setting, a few-shot setting, and supervised setting using all available training data. We obtain substantially higher zero-shot F1-scores for 3 out of 4 languages than previous approaches and significantly exceed previous supervised state-of-the-art results for all five tested languages. We provide the code and models as open source.1
44
Ferreira Cruz, André, Gil Rocha, and Henrique Lopes Cardoso. "Coreference Resolution: Toward End-to-End and Cross-Lingual Systems." Information 11, no. 2 (January 30, 2020): 74. http://dx.doi.org/10.3390/info11020074.
Full textAbstract:
The task of coreference resolution has attracted considerable attention in the literature due to its importance in deep language understanding and its potential as a subtask in a variety of complex natural language processing problems. In this study, we outlined the field’s terminology, describe existing metrics, their differences and shortcomings, as well as the available corpora and external resources. We analyzed existing state-of-the-art models and approaches, and reviewed recent advances and trends in the field, namely end-to-end systems that jointly model different subtasks of coreference resolution, and cross-lingual systems that aim to overcome the challenges of less-resourced languages. Finally, we discussed the main challenges and open issues faced by coreference resolution systems.
45
Zheng, Boyuan, Patrick Xia, Mahsa Yarmohammadi, and Benjamin Van Durme. "Multilingual Coreference Resolution in Multiparty Dialogue." Transactions of the Association for Computational Linguistics 11 (2023): 922–40. http://dx.doi.org/10.1162/tacl_a_00581.
Full textAbstract:
Abstract Existing multiparty dialogue datasets for entity coreference resolution are nascent, and many challenges are still unaddressed. We create a large-scale dataset, Multilingual Multiparty Coref (MMC), for this task based on TV transcripts. Due to the availability of gold-quality subtitles in multiple languages, we propose reusing the annotations to create silver coreference resolution data in other languages (Chinese and Farsi) via annotation projection. On the gold (English) data, off-the-shelf models perform relatively poorly on MMC, suggesting that MMC has broader coverage of multiparty coreference than prior datasets. On the silver data, we find success both using it for data augmentation and training from scratch, which effectively simulates the zero-shot cross-lingual setting.
46
Eloundou Eloundou, Girex. "Cláusulas absolutas y construcciones afines en español: la correferencia y la presencia/ausencia del sujeto como rasgos distintivos." Futhark. Revista de Investigación y Cultura, no. 15 (2020): 11–24. http://dx.doi.org/10.12795/futhark.2020.i15.04.
Full textAbstract:
The questions of the coreference of the NP-subject with an element of the main sentence and that of its presence or absence are some of the most debated in grammars as far as the absolute clauses are concerned. The objective pursued in this work is to demonstrate that these syntactic features (coreference and presence / absence) of the subject make it possible to distinguish absolute clauses from related structures such as concerted constructions, incidental adjectives, semiabsolute and pseudo-absolute clauses. In the analysis, we base ourselves on a descriptive perspective with a traditional terminology, and sometimes we resort to the corresponding Latin structures to highlight the formal and structural differences induced by the coreference and the presence / absence of the subject in these constructions
47
Sapena, Emili, Lluís Padró, and Jordi Turmo. "A Constraint-Based Hypergraph Partitioning Approach to Coreference Resolution." Computational Linguistics 39, no. 4 (December 2013): 847–84. http://dx.doi.org/10.1162/coli_a_00151.
Full textAbstract:
This work is focused on research in machine learning for coreference resolution. Coreference resolution is a natural language processing task that consists of determining the expressions in a discourse that refer to the same entity. The main contributions of this article are (i) a new approach to coreference resolution based on constraint satisfaction, using a hypergraph to represent the problem and solving it by relaxation labeling; and (ii) research towards improving coreference resolution performance using world knowledge extracted from Wikipedia. The developed approach is able to use an entity-mention classification model with more expressiveness than the pair-based ones, and overcome the weaknesses of previous approaches in the state of the art such as linking contradictions, classifications without context, and lack of information evaluating pairs. Furthermore, the approach allows the incorporation of new information by adding constraints, and research has been done in order to use world knowledge to improve performances. RelaxCor, the implementation of the approach, achieved results at the state-of-the-art level, and participated in international competitions: SemEval-2010 and CoNLL-2011. RelaxCor achieved second place in CoNLL-2011.
48
Li, Jie, Yanchang Lu, and Zhenxuan Liang. "Pairwise Cross-Document Event Coreference Resolution with Contrastive Learning." Advances in Education, Humanities and Social Science Research 5, no. 1 (April 25, 2023): 127. http://dx.doi.org/10.56028/aehssr.5.1.127.2023.
Full textAbstract:
Cross-Document (CD) Event Coreference Resolution (ECR) is a fundamental task in Natural Language processing (NLP) and Knowledge Base Population (KBP). Resolving the event coreference relationship is a challenging task, which necessitates a thorough semantic comprehension of the events. Existing methods have spontaneously formulated this problem as a binary classification task based on sentence segments. However, the information distributed in the longer context is ignored by most prior works. Recent event coreference works focus on adding auxiliary information to improve the performance. The information such as involved entity information, structural information or database queried information is extracted from related documents as long context. Whereas extraction error, matching error and other types of error are introduced in the process of obtaining related information when the context is incomplete. In this work, we present a Contrastive Learning based Pairwise Event Coreference (CLPEC) framework to complete and optimize the CD-ECR task utilizing contextual information with contrastive learning technology. We also adopt augmentation technology to preprocess event representations and improve our performance. Experiment results show that we achieve competitive results on a number of key metrics on the ECB+ corpus.
49
Rysová, Magdaléna. "Studying text coherence in Czech – a corpus-based analysis." Topics in Linguistics 18, no. 2 (December 20, 2017): 36–47. http://dx.doi.org/10.1515/topling-2017-0009.
Full textAbstract:
Abstract The paper deals with the field of Czech corpus linguistics and represents one of various current studies analysing text coherence through language interactions. It presents a corpusbased analysis of grammatical coreference and sentence information structure (in terms of contextual boundness) in Czech. It focuses on examining the interaction of these two language phenomena and observes where they meet to participate in text structuring. Specifically, the paper analyses contextually bound and non-bound sentence items and examines whether (and how often) they are involved in relations of grammatical coreference in Czech newspaper articles. The analysis is carried out on the language data of the Prague Dependency Treebank (PDT) containing 3,165 Czech texts. The results of the analysis are helpful in automatic text annotation - the paper presents how (or to what extent) the annotation of grammatical coreference may be used in automatic (pre-)annotation of sentence information structure in Czech. It demonstrates how accurately we may (automatically) assume the value of contextual boundness for the antecedent and anaphor (as the two participants of a grammatical coreference relation). The results of the paper demonstrate that the anaphor of grammatical coreference is automatically predictable - it is a non-contrastive contextually bound sentence item in 99.18% of cases. On the other hand, the value of contextual boundness of the antecedent is not so easy to estimate (according to the PDT, the antecedent is contextually non-bound in 37% of cases, non-contrastive contextually bound in 50% and contrastive contextually bound in 13% of cases).
50
Ogrodniczuk, Maciej. "Nominal coreference resolution for Polish." Poznan Studies in Contemporary Linguistics 55, no. 2 (June 26, 2019): 367–96. http://dx.doi.org/10.1515/psicl-2019-0014.
Full textAbstract:
Abstract The article presents current research on coreference resolution for Polish, from development of a sufficiently general model of reference relations to implementation of tools using this model to automatically detect coreference in written texts. The task is accomplished using corpus approach, with manual annotation of reference structures, verification of the proposed theory on the corpus data, implementation of automatic tools in different technical architectures and finally assessing their quality using standard evaluation methods.