Littérature scientifique sur le sujet « Paraphrase »

Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres

Choisissez une source :

Consultez les listes thématiques d’articles de revues, de livres, de thèses, de rapports de conférences et d’autres sources académiques sur le sujet « Paraphrase ».

À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.

Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.

Articles de revues sur le sujet "Paraphrase"

1

ZHANG, YUJIE, et KAZUHIDE YAMAMOTO. « Paraphrasing spoken Chinese using a paraphrase corpus ». Natural Language Engineering 11, no 4 (10 novembre 2005) : 417–34. http://dx.doi.org/10.1017/s1351324905003712.

Texte intégral
Résumé :
One of the key issues in spoken-language translation is how to deal with unrestricted expressions in spontaneous utterances. We have developed a paraphraser for use as part of a translation system, and in this paper we describe the implementation of a Chinese paraphraser for a Chinese-Japanese spoken-language translation system. When an input sentence cannot be translated by the transfer engine, the paraphraser automatically transforms the sentence into alternative expressions until one of these alternatives can be translated by the transfer engine. Two primary issues must be dealt with in paraphrasing: how to determine new expressions, and how to retain the meaning of the input sentence. We use a pattern-based approach in which the meaning is retained to the greatest possible extent without deep parsing. The paraphrase patterns are acquired from a paraphrase corpus and human experience. The paraphrase instances are automatically extracted and then generalized into paraphrase patterns. A total of 1719 paraphrase patterns obtained using this method and an implemented paraphraser were used in a paraphrasing experiment. The results showed that the implemented paraphraser generated 1.7 paraphrases on average for each test sentence and achieved an accuracy of 88%.
Styles APA, Harvard, Vancouver, ISO, etc.
2

Çeşme, Hatice. « Exploring Paraphrase Performances and Strategies of Graduate Student Writing ». Shanlax International Journal of Education 11, no 1 (1 décembre 2022) : 10–23. http://dx.doi.org/10.34293/education.v11i1.5247.

Texte intégral
Résumé :
This study aims to investigate performances and strategies of EFL graduate students in terms of language proficiency, language background and type of writing task. The participants were 12 graduate students pursuing their doctoral studies in ELT at a Turkish university. A chosen text was used for data collection and the students’ paraphrased texts were analyzed employing Keck’s (2006) the taxonomy of paraphrase types and ‘a paraphrase found form’ developed by the researcher in terms of lexical and structural changes. The results of the study revealed that graduate students had challenges in appropriate implementation of paraphrasing in their task. While they generated frequently moderate level of paraphrases, the strategies they often used were synonym substitution as well as copying strings of words from source. Additionally, deviated meaning was designated as a new paraphrase type in the taxonomy of paraphrase. These findings suggest that students need an explicit paraphrasing instruction supported by good and bad paraphrase examples and more practice to learn how to paraphrase appropriately.
Styles APA, Harvard, Vancouver, ISO, etc.
3

Isu, Rudolof J. « Lexical Paraphrases in Tonis (a Poetry of Dawan or Uab Meto) Marriage Process in South Central Timor District ». Rainbow : Journal of Literature, Linguistics and Culture Studies 13, no 1 (30 avril 2024) : 65–73. http://dx.doi.org/10.15294/rainbow.v13i1.2960.

Texte intégral
Résumé :
This paper is entitled Lexical Paraphrase in Tonis (Dawan Poetry or Uab Meto) used in the Marriage Process in South Central Timor District. The problem of this paper is whether the speech in tonis in Dawan ethnic can show lexical paraphrase both lexical paraphrase on noun, lexical paraphrase on adverb, lexical paraphrase on adjective and lexical paraphrase on preposition. The purpose of this research is to find out whether there is a paraphrasing process in the speech of the marriage process in South Central Timor District. The topic or title mentioned above is considered to have its own uniqueness in language style and distinctiveness in speech. This research uses a qualitative approach method. The results of this study show that there are fifty lexical paraphrases on verbs, twenty-four lexical paraphrases on nouns, eleven lexical paraphrases on adverbs, four lexical paraphrases on adjectives, and one lexical paraphrase on prepositions
Styles APA, Harvard, Vancouver, ISO, etc.
4

Nicula, Bogdan, Mihai Dascalu, Natalie N. Newton, Ellen Orcutt et Danielle S. McNamara. « Automated Paraphrase Quality Assessment Using Language Models and Transfer Learning ». Computers 10, no 12 (6 décembre 2021) : 166. http://dx.doi.org/10.3390/computers10120166.

Texte intégral
Résumé :
Learning to paraphrase supports both writing ability and reading comprehension, particularly for less skilled learners. As such, educational tools that integrate automated evaluations of paraphrases can be used to provide timely feedback to enhance learner paraphrasing skills more efficiently and effectively. Paraphrase identification is a popular NLP classification task that involves establishing whether two sentences share a similar meaning. Paraphrase quality assessment is a slightly more complex task, in which pairs of sentences are evaluated in-depth across multiple dimensions. In this study, we focus on four dimensions: lexical, syntactical, semantic, and overall quality. Our study introduces and evaluates various machine learning models using handcrafted features combined with Extra Trees, Siamese neural networks using BiLSTM RNNs, and pretrained BERT-based models, together with transfer learning from a larger general paraphrase corpus, to estimate the quality of paraphrases across the four dimensions. Two datasets are considered for the tasks involving paraphrase quality: ULPC (User Language Paraphrase Corpus) containing 1998 paraphrases and a smaller dataset with 115 paraphrases based on children’s inputs. The paraphrase identification dataset used for the transfer learning task is the MSRP dataset (Microsoft Research Paraphrase Corpus) containing 5801 paraphrases. On the ULPC dataset, our BERT model improves upon the previous baseline by at least 0.1 in F1-score across the four dimensions. When using fine-tuning from ULPC for the children dataset, both the BERT and Siamese neural network models improve upon their original scores by at least 0.11 F1-score. The results of these experiments suggest that transfer learning using generic paraphrase identification datasets can be successful, while at the same time obtaining comparable results in fewer epochs.
Styles APA, Harvard, Vancouver, ISO, etc.
5

Michiels, Paul, Karyn Kessler et Paul Rogers. « Paraphrase Patterns of Expert Academic Writers : Implications for Writing Development, Writing Pedagogy, and Plagiarism Policies ». Literatura y Lingüística, no 46 (13 février 2023) : 153–89. http://dx.doi.org/10.29344/0717621x.46.3133.

Texte intégral
Résumé :
This study offers a linguistic analysis of language borrowing in expertly produced paraphrases. Within the context of higher education, paraphrase writing, an essential skill for source-based writing tasks across the curriculum and a key component in the development of disciplinary expertise, represents a challenge for students and teachers because 1) there is no precise and generally accepted definition of acceptable academic paraphrase, 2) discussions of paraphrase are more often framed in terms of plagiarism than effective writing, and 3) little is known about the linguistic (or rhetorical dimensions) of paraphrases in writing published by experts. The present study analyzes five corpora of paraphrase/source passage pairs (n = 233) produced by expert writers. Corpora 1 and 2 contain exemplar paraphrase/source passage pairs drawn from writing guides and handbooks designed for college students. The remaining three corpora of paraphrase/source passage pairings were assembled using award-winning published articles in three disciplines. Using Keck’s (2006) taxonomy for classifying paraphrases, the study found that about 27% of the average paraphrase of the expert writers analyzed here is made up of language found in the source passage. Paraphrase patterns of expert academic writers point toward a potential continuum of acceptable language borrowing practices likely driven by disciplinary differences. Implications for writing development, writing pedagogy, plagiarism policy, and further research are discussed.
Styles APA, Harvard, Vancouver, ISO, etc.
6

Bloemendal, Jan. « Exegesis and Hermeneutics in Erasmus’ Paraphrase on Luke ». Erasmus Studies 36, no 2 (2016) : 148–62. http://dx.doi.org/10.1163/18749275-03602006.

Texte intégral
Résumé :
This article discusses how Erasmus deals with the personae in the Paraphrase on Luke, distinguishing between the author Erasmus (the paraphrast), the narrator (the paraphraser) and the evangelist. These ‘Luke-voices’ are connected to exegesis (explanation of the narrative) and hermeneutics (the application of the narrative to the lives of the audience). It is argued that Erasmus deliberately played with the voices; this enabled him to criticize wrongs of his own times as worded by ‘Luke’, and to contribute to the advancement of Christian piety.
Styles APA, Harvard, Vancouver, ISO, etc.
7

Bhagat, Rahul, et Eduard Hovy. « What Is a Paraphrase ? » Computational Linguistics 39, no 3 (septembre 2013) : 463–72. http://dx.doi.org/10.1162/coli_a_00166.

Texte intégral
Résumé :
Paraphrases are sentences or phrases that convey the same meaning using different wording. Although the logical definition of paraphrases requires strict semantic equivalence, linguistics accepts a broader, approximate, equivalence—thereby allowing far more examples of “quasi-paraphrase.” But approximate equivalence is hard to define. Thus, the phenomenon of paraphrases, as understood in linguistics, is difficult to characterize. In this article, we list a set of 25 operations that generate quasi-paraphrases. We then empirically validate the scope and accuracy of this list by manually analyzing random samples of two publicly available paraphrase corpora. We provide the distribution of naturally occurring quasi-paraphrases in English text.
Styles APA, Harvard, Vancouver, ISO, etc.
8

Zhou, Ying, Xiaokang Hu et Vera Chung. « Automatic Construction of Fine-Grained Paraphrase Corpora System Using Language Inference Model ». Applied Sciences 12, no 1 (5 janvier 2022) : 499. http://dx.doi.org/10.3390/app12010499.

Texte intégral
Résumé :
Paraphrase detection and generation are important natural language processing (NLP) tasks. Yet the term paraphrase is broad enough to include many fine-grained relations. This leads to different tolerance levels of semantic divergence in the positive paraphrase class among publicly available paraphrase datasets. Such variation can affect the generalisability of paraphrase classification models. It may also impact the predictability of paraphrase generation models. This paper presents a new model which can use few corpora of fine-grained paraphrase relations to construct automatically using language inference models. The fine-grained sentence level paraphrase relations are defined based on word and phrase level counterparts. We demonstrate that the fine-grained labels from our proposed system can make it possible to generate paraphrases at desirable semantic level. The new labels could also contribute to general sentence embedding techniques.
Styles APA, Harvard, Vancouver, ISO, etc.
9

Vanautgaerden, Alexandre. « Les Paraphrases d’Érasme : Paraphrase sur Matthieu ». Moreana 39 (Number 150), no 2 (juin 2002) : 4–6. http://dx.doi.org/10.3366/more.2002.39.2.3.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
10

Gibson, Rhonda, et Dolf Zillmann. « Effects of Citation in Exemplifying Testimony on Issue Perception ». Journalism & ; Mass Communication Quarterly 75, no 1 (mars 1998) : 167–76. http://dx.doi.org/10.1177/107769909807500116.

Texte intégral
Résumé :
Two sides of an issue were presented and exemplified with testimonials in a magazine-style news report. Testimony featured the interviewees' positions in citation or paraphrase. All combinations of citation-paraphrase were created and analyzed in factorial designs; i.e., position A (cited, paraphrased) was crossvaried with position B (cited, paraphrased). Issue perception was found to be greatly influenced by citation. Respondents adopted the cited position more than the paraphrased position. This effect was most pronounced when the opposing position was paraphrased. No presentation bias was detected, however.
Styles APA, Harvard, Vancouver, ISO, etc.

Thèses sur le sujet "Paraphrase"

1

Eyecioglu, Ozmutlu Asli. « Paraphrase identification using knowledge-lean techniques ». Thesis, University of Sussex, 2016. http://sro.sussex.ac.uk/id/eprint/65497/.

Texte intégral
Résumé :
This research addresses the problem of identification of sentential paraphrases; that is, the ability of an estimator to predict well whether two sentential text fragments are paraphrases. The paraphrase identification task has practical importance in the Natural Language Processing (NLP) community because of the need to deal with the pervasive problem of linguistic variation. Accurate methods for identifying paraphrases should help to improve the performance of NLP systems that require language understanding. This includes key applications such as machine translation, information retrieval and question answering amongst others. Over the course of the last decade, a growing body of research has been conducted on paraphrase identification and it has become an individual working area of NLP. Our objective is to investigate whether techniques concentrating on automated understanding of text requiring less resource may achieve results comparable to methods employing more sophisticated NLP processing tools and other resources. These techniques, which we call “knowledge-lean”, range from simple, shallow overlap methods based on lexical items or n-grams through to more sophisticated methods that employ automatically generated distributional thesauri. The work begins by focusing on techniques that exploit lexical overlap and text-based statistical techniques that are much less in need of NLP tools. We investigate the question “To what extent can these methods be used for the purpose of a paraphrase identification task?” For the two gold standard data, we obtained competitive results on the Microsoft Research Paraphrase Corpus (MSRPC) and reached the state-of-the-art results on the Twitter Paraphrase Corpus, using only n-gram overlap features in conjunction with support vector machines (SVMs). These techniques do not require any language specific tools or external resources and appear to perform well without the need to normalise colloquial language such as that found on Twitter. It was natural to extend the scope of the research and to consider experimenting on another language, which is poor in resources. The scarcity of available paraphrase data led us to construct our own corpus; we have constructed a paraphrasecorpus in Turkish. This corpus is relatively small but provides a representative collection, including a variety of texts. While there is still debate as to whether a binary or fine-grained judgement satisfies a paraphrase corpus, we chose to provide data for a sentential textual similarity task by agreeing on fine-grained scoring, knowing that this could be converted to binary scoring, but not the other way around. The correlation between the results from different corpora is promising. Therefore, it can be surmised that languages poor in resources can benefit from knowledge-lean techniques. Discovering the strengths of knowledge-lean techniques extended with a new perspective to techniques that use distributional statistical features of text by representing each word as a vector (word2vec). While recent research focuses on larger fragments of text with word2vec, such as phrases, sentences and even paragraphs, a new approach is presented by introducing vectors of character n-grams that carry the same attributes as word vectors. The proposed method has the ability to capture syntactic relations as well as semantic relations without semantic knowledge. This is proven to be competitive on Twitter compared to more sophisticated methods.
Styles APA, Harvard, Vancouver, ISO, etc.
2

Daunay, Bertrand. « La paraphrase dans l'approche scolaire des textes littéraires : étude didactique ». Lille 3, 1999. http://www.theses.fr/1999LIL30015.

Texte intégral
Résumé :
L'interdit de la paraphrase dans l'explication de texte littéraire repose sur des principes théoriquement fragiles et une définition instable de la paraphrase : il ne porte pas sur un discours métatextuel identifiable mais sur un effet discursif. Telle est la thèse de ce travail qui aborde le phénomène de la paraphrase dans l'approche scolaire des textes littéraires en diachronie comme en synchronie. Une telle approche aboutit à une réhabilitation de la paraphrase, qui passe notamment par une réévaluation de son rôle effectif dans l'apprentissage de l'écriture comme de la lecture. Une première partie envisage historiquement la pratique de la paraphrase dans le rapport (scolaire ou non) au texte littéraire de l'Antiquité à nos jours. Une deuxième partie décrit les conditions et les formes de la disqualification de la paraphrase dans l'explication de texte depuis le XIXe siècle, pour faire ressortir l'impossibilité d'une définition objective de la paraphrase dans ce contexte. D'où la nécessité d'établir, dans une troisième partie, ce qui amène un évaluateur à considérer qu'un énoncé est ou non paraphrastique, autrement dit à émettre un jugement métatextuel d'identification- qui n'est en fait qu'un jugement d'acceptabilité de la paraphrase ; les conditions de ce jugement se ramènent essentiellement à la présence dans le métatexte de marques discursives d'une distance avec le texte-source. La paraphrase est ensuite (quatrième partie) définie comme formulation de la compréhension- donc comme activité à la fois cognitive et discursive inhérente à tout discours métatextuel : c'est sur ces bases que peuvent être proposées (dans une cinquième partie) des démarches d'apprentissage visant au développement métatextuel des élèves par l'évaluation et la discussion des frontières entre diverses réalisations discursives et des effets de réception de leurs propres productions métatextuelles
The prohibition of paraphrase in appreciation of literary text rests on principles theoretically uncertain, as well as an unstable definition of paraphrase : it does not relate to an identified metatextual discourse, but to a discursive effect. Such is the thesis of this work wich approaches paraphrasing in the academic apprehension of literary texts, both diachronically and synchronically. Such an approach results in the rehabilitation of paraphrase, through a renewed appraisal of the part it takes in fact in learning to write and read too. The first part is a historical survey of the practise of paraphrase in its – academic or not – relationship to literary text from Antiquity up to now. The second part describes the conditions and forms of the disqualification of paraphrase in appreciation of literary text since the XIXth century, in order to emphasise on the impossibility for any objective definition of paraphrase in that context. Therefore it is necessary to establish, in the third part, what may allow the appraiser to tell what is paraphrasing and what is not, i. E. To express a metatextual judgement essentially come down to the presence of a distance between discursive marks in the metatext, and the root-text. In part four, paraphrase is shown as the expression of understanding – and thus as an activity, both discursive and cognitive – related to metatextual discourse : on these bases, the fifth part propounds learning methods aiming at the metatextual development of students through the appreciation and discussion of the borders between different discursive realisations, and the effects of reception to their own metatextual productions
Styles APA, Harvard, Vancouver, ISO, etc.
3

Bouamor, Houda. « Etude de la paraphrase sous-phrastique en traitement automatique des langues ». Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00717702.

Texte intégral
Résumé :
La variabilité en langue est une source majeure de difficultés dans la plupart des applications du traitement automatique des langues. Elle se manifeste dans le fait qu'une même idée ou un même événement peut être exprimé avec des mots ou des groupes de mots différents ayant la même signification dans leur contexte respectif. Capturer automatiquement des équivalences sémantiques entre des unités de texte est une tâche complexe mais qui s'avère indispensable dans de nombreux contextes. L'acquisition a priori de listes d'équivalences met à disposition des ressources utiles pour, par exemple, améliorer le repérage d'une réponse à une question, autoriser des formulations différentes en évaluation de la traduction automatique, ou encore aider des auteurs à trouver des formulations plus adaptées. Dans cette thèse, nous proposons une étude détaillée de la tâche d'acquisition de paraphrases sous-phrastiques à partir de paires d'énoncés sémantiquement liés. Nous démontrons empiriquement que les corpus parallèles monolingues, bien qu'extrêmement rares, constituent le type de ressource le plus adapté pour ce genre d'étude. Nos expériences mettent en jeu cinq techniques d'acquisition, représentatives de différentes approches et connaissances, en anglais et en français. Afin d'améliorer la performance en acquisition, nous réalisons la combinaison des paraphrases produites par ces techniques par une validation reposant sur un classifieur automatique à maximum d'entropie bi-classe. Un résultat important de notre étude est l'identification de paraphrases qui défient actuellement les techniques étudiées, lesquelles sont classées et quantifiées en anglais et français. Nous examinons également dans cette thèse l'impact de la langue, du type du corpus et la comparabilité des paires des énoncés utilisés sur la tâche d'acquisition de paraphrases sous- phrastiques. Nous présentons le résultat d'une analyse de la performance des différentes méthodes testées en fonction des difficultés d'alignement des paires de paraphrases d'énoncés. Nous donnons, ensuite, un compte rendu descriptif et quantitatif des caractéristiques des paraphrases trouvées dans les différents types de corpus étudiés ainsi que celles qui défient les approches actuelles d'identification automatique.
Styles APA, Harvard, Vancouver, ISO, etc.
4

AMGHAR, TASSADIT. « Une contribution a la modelisation informatique du phenomene de paraphrase : le jugement de paraphrase et la metonymie ». Nantes, 1996. http://www.theses.fr/1996NANT2068.

Texte intégral
Résumé :
Cette these porte sur un aspect du traitement automatique des langues naturelles ecrites. Dans cette premiere partie nous proposons une modelisation du jugement de paraphrase correspondant aux analyses linguistiques developpees par c. Fuchs. Nous sommes ainsi conduite a opposer ce que nous qualifions de diagnostic de paraphrase au jugement binaire et a la notion d'identite semantique habituellement proposes pour rendre compte de l'existence d'une relation de paraphrasticite entre enonces. Le diagnostic de paraphrase realise par le systeme paraph, entre deux enonces decrit les choix interpretatifs et les approximations semantiques qui legitiment l'equivalence entre les enonces. La methodologie adoptee vise a caracteriser des significations difficiles a cerner telles que celles de certaines categories grammaticales (aspect, modalites etc. ) dont les valeurs exprimees en contexte par l'auxiliaire modal pouvoir sont une bonne illustration. Nous avons aussi etudie ce que recouvre le phenomene lorsqu'il est qualifie de reformulation dans les systemes de recherche d'information. Une deuxieme partie concerne ce que l'on peut considerer comme une forme de paraphrase mettant en jeu un phenomene d'ellipse: la metonymie. Quelquefois consideree comme un phenomene de glissement de sens ou cantonnee dans la classe des figures de style, le phenomene est analyse ici comme une forme de reference langagiere. Nous lui consacrons une analyse dans laquelle nous nous appuyons sur le formalisme des graphes conceptuels de j. Sowa pour modeliser le passage entre un enonce comportant une ellipse methonymique et un enonce dans lequel le phenomene n'intervient plus
Styles APA, Harvard, Vancouver, ISO, etc.
5

Greenwood, D. S. « The seventeenth-century English poetic biblical paraphrase ». Thesis, University of Cambridge, 1985. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.304373.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
6

Kampeera, Wannachai. « Analyse linguistique et formalisation pour le traitement automatique de la paraphrase ». Thesis, Besançon, 2013. http://www.theses.fr/2013BESA1011/document.

Texte intégral
Résumé :
Les relations paraphrastiques entre plusieurs ensembles de paraphrasespeuvent se décrire en termes de suites de transformations textuelles. Pour qu’il aitparaphrase, il faut qu’une substitution lexicale noyau se mette en route entrainantd’autres modifications syntaxiques, lexicales et morphologiques.Après avoir décrit les mécanismes de paraphrasage récurrents, nous avons proposédeux formalisations. La première est théorique et explique les différentes relationsparaphrastiques entretenues par les paraphrases entre-elles. La deuxième,tournée vers des applications, formalise les structures paraphrastiques sous-formede prédicats-arguments. Nous considérons cette dernière adaptée au traitementautomatique de la paraphrase.Nous avons à la suite implémenté un système d’extraction de structures paraphrastiques.Il s’agit d’un système opérationnel appliqué à un volume de donnéesrelevant de notre domaine d’étude, et dont le but est de donner un exemple concretd’emploi possible de notre formalisation.Mots-clés : paraphrase, structures paraphrastiques, traitement automatique dela paraphrase, extraction des structures paraphrastiques
The relations between sets of paraphrases can be described as seriesof textual transformations. To rephrase, an initial lexical substitution starts, thentriggers other syntactic, lexical and morphological changes.After having described the frequent paraphrasing mechanisms in our corpus,we propose two formalisations. The first one is theoretical, explaining the differentparaphrasing relationships maintained by the paraphrases between each other. Thesecond formalises paraphrase structures as predicate-argument ones. We considerthe latter suitable for paraphrase processing.Finally we have implemented a paraphrase structures extraction system. Thisis a compact operational system for the volume of data within our domain, the aimof which is to provide a concrete example of a possible use of our formalisation
Styles APA, Harvard, Vancouver, ISO, etc.
7

Milićević, Jasmina. « Modélisation sémantique, syntaxique et lexicale de la paraphrase ». [Montréal] : Université de Montréal, 2003. http://wwwlib.umi.com/cr/umontreal/fullcit?pNQ82712.

Texte intégral
Résumé :
Thèse (Ph. D.)--Université de Montréal, 2003.
"NQ-82712." "Thèse présentée à la faculté des études supérieures en vue de l'obtention du grade de philosophiae doctor (Ph. D.) en linguistique." Ex. 3: Photocopie. Version électronique également disponible sur Internet.
Styles APA, Harvard, Vancouver, ISO, etc.
8

Otrusina, Lubomír. « Lze to říci jinak aneb automatické hledání parafrází ». Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2009. http://www.nusl.cz/ntk/nusl-236669.

Texte intégral
Résumé :
Automatic paraphrase discovery is an important task in natural language processing. Many systems use paraphrases for improve performance e.g. systems for question answering, information retrieval or document summarization. In this thesis, we explain basic concepts e.g. paraphrase or paraphrase pattern. Next we propose some methods for paraphrase discovery from various resources. Subsequently we propose an unsupervised method for discovering paraphrase from large plain text based on context and keywords between NE pairs. In the end we explain evaluation metods in paraphrase discovery area and then we evaluate our system and compare it with similar systems.
Styles APA, Harvard, Vancouver, ISO, etc.
9

Kim, Mi-Jin. « Comparative Analysis of the Musical Distortion in Kaikhosru Sorabji’s and Vladimir Horowitz’s Piano Paraphrases Based on Bizet’s Opera Carmen ». Thesis, University of North Texas, 2014. https://digital.library.unt.edu/ark:/67531/metadc699924/.

Texte intégral
Résumé :
This study focuses on a comparative analysis of two piano paraphrases, Pastiche on Habanera from ‘Carmen’ by Kaikhosru Sorabji and Variations on a Theme from Bizet’s ‘Carmen’ by Vladimir Horowitz. These compositions idiomatically distort the original material in a manner that was not explored up to the moment of their respective conception. They expose each composer’s free compositional approach, reflecting musical freedom rooted in the originality of their musical thinking. The aesthetic uniqueness of these two compositions strongly stimulates and justifies academic interest to explore their technical construction, musical differences, and artistic significance. This study proposes to undertake a comparative study of these two compositions, analyzing (1) aspects of the musical character, which are linked with embellishment, or rearrangement of original material, and (2) differences in performance approach based on recorded examples and critical observations by others of the performances of these works by Sorabji and Horowitz.
Styles APA, Harvard, Vancouver, ISO, etc.
10

Walton, Mathew. « Issues of Narrativity in the Romantic Piano Opera Paraphrase ». Thèse, Université d'Ottawa / University of Ottawa, 2012. http://hdl.handle.net/10393/20502.

Texte intégral
Résumé :
Although the opera paraphrase was once a cornerstone of the virtuoso pianist's repertoire, as a genre it has traditionally been neglected by a scholarship which prioritizes authenticity and original compositional thought. By approaching this repertoire from a critical standpoint concerned with the production of narrative, this thesis demonstrates the true value of the paraphrase. A review of the current literature on narrative, gesture, and the paraphrase reveals major gaps in the state of research, and this thesis addresses these issues by presenting analyses of several works, in both printed and performed forms. The chapter “Settling the Score” interrogates the score, and argues that through their choice, ordering, and setting of operatic themes in a paraphrase, composers can alter or recreate the narrative of the source opera. By analyzing and comparing by reading the narrative schemes of seven different paraphrases based on Mozart's Don Giovanni, the chapter highlights the agency of the arranger in the production of narrative. The next chapter, entitled “Playing the Part,” suggests that the creation of narrative also extends beyond the work of the composer to encompass the role of the performer. By comparing the use of physical gestures in two video-recorded performances of Liszt's paraphrase Réminiscences de Don Juan, the thesis postulates that a pianist's gestures can influence the audience's perception of narrative. In an attempt to centralize the voice of the performer, the chapter also includes reflective analysis of the author's own performances of Liszt's paraphrase. By employing analytical methods which focus on the production of musical narrative, this thesis demonstrates that the paraphrase is worthy of greater attention, both in scholarship and performance.
Styles APA, Harvard, Vancouver, ISO, etc.

Livres sur le sujet "Paraphrase"

1

Erasmus, Desiderius. Paraphrase on John. Toronto : University of Toronto Press, 1991.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
2

Erasmus, Desiderius. Paraphrase on Luke. Toronto : University of Toronto Press, 2002.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
3

Fuchs, Catherine. Paraphrase et énonciation. Gap [France] : Ophrys, 1994.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
4

Erasmus, Desiderius. Paraphrase on Matthew. Sous la direction de Simpson Dean et Sider Robert D. Toronto [Ont.] : University of Toronto Press, 2008.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
5

Erasmus, Desiderius. Paraphrase on Matthew. Sous la direction de Simpson Dean et Sider Robert D. Toronto [Ont.] : University of Toronto Press, 2008.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
6

Erasmus, Desiderius. Paraphrase on John. Toronto : University of Toronto Press, 1991.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
7

Erasmus, Desiderius. Paraphrase on Matthew. Sous la direction de Simpson Dean et Sider Robert D. Toronto [Ont.] : University of Toronto Press, 2008.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
8

Erasmus, Desiderius. Paraphrase on Mark. Toronto : University of Toronto Press, 1988.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
9

1805-1868, Stifter Adalbert, dir. Waldwand : Eine Paraphrase. Berlin : Matthes & Seitz Berlin, 2016.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
10

Daunay, Bertrand. Éloge de la paraphrase. Saint-Denis : Presses universitaires de Vincennes, 2002.

Trouver le texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.

Chapitres de livres sur le sujet "Paraphrase"

1

Schneider, Birgit, Beate Löffler, Tino Mager et Carola Hein. « #PARAPHRASE ». Dans Digital Humanities Research, 45–46. Bielefeld, Germany : Bielefeld University Press / transcript Verlag, 2023. http://dx.doi.org/10.14361/9783839469132-005.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
2

Sidoli, Nathan, et R. S. D. Thomas. « Paraphrase ». Dans The Spherics of Theodosios, 363–473. London : Routledge, 2023. http://dx.doi.org/10.4324/9781003142164-8.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
3

Kanerva, Jenna, Filip Ginter, Li-Hsin Chang, Valtteri Skantsi, Jemina Kilpeläinen, Hanna-Mari Kupari, Aurora Piirto, Jenna Saarni, Maija Sevón et Otto Tarkka. « Textual Paraphrase Dataset for Deep Language Modelling ». Dans European Language Grid, 343–48. Cham : Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-17258-8_27.

Texte intégral
Résumé :
AbstractThe Turku Paraphrase Corpus is a dataset of over 100,000 Finnish paraphrase pairs. During the corpus creation, we strived to gather challenging paraphrase pairs, more suitable to test the capabilities of natural language understanding models. The paraphrases are both selected and classified manually, so as to minimise lexical overlap, and provide examples that are structurally and lexically different to the maximum extent. An important distinguishing feature of the corpus is that most of the paraphrase pairs are extracted and distributed in their native document context, rather than in isolation. The primary application for the dataset is the development and evaluation of deep language models, and representation learning in general.
Styles APA, Harvard, Vancouver, ISO, etc.
4

Fowler, Roger. « Poetic Paraphrase ». Dans Old English Prose and Verse, 114–23. London : Routledge, 2022. http://dx.doi.org/10.4324/9781003273226-10.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
5

Pivovarova, Lidia, Ekaterina Pronoza, Elena Yagunova et Anton Pronoza. « ParaPhraser : Russian Paraphrase Corpus and Shared Task ». Dans Communications in Computer and Information Science, 211–25. Cham : Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-71746-3_18.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
6

Bouamor, Houda, Aurélien Max et Anne Vilnat. « Comparison of Paraphrase Acquisition Techniques on Sentential Paraphrases ». Dans Advances in Natural Language Processing, 67–78. Berlin, Heidelberg : Springer Berlin Heidelberg, 2010. http://dx.doi.org/10.1007/978-3-642-14770-8_9.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
7

Danelutto, M., K. Hammond et H. Gonzalez-Velez. « ParaPhrase Workshop 2012 ». Dans Lecture Notes in Computer Science, 368–69. Berlin, Heidelberg : Springer Berlin Heidelberg, 2013. http://dx.doi.org/10.1007/978-3-642-36949-0_40.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
8

Arthur, Jake. « Biblical Verse Paraphrase ». Dans The Palgrave Encyclopedia of Early Modern Women's Writing, 1–7. Cham : Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-01537-4_34-1.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
9

Arthur, Jake. « Biblical Verse Paraphrase ». Dans The Palgrave Encyclopedia of Early Modern Women's Writing, 1–7. Cham : Springer International Publishing, 2023. http://dx.doi.org/10.1007/978-3-030-01537-4_34-2.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
10

Hausser, Roland. « Paraphrase and Ambiguity ». Dans Ontology of Communication, 229–38. Cham : Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-22739-4_18.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.

Actes de conférences sur le sujet "Paraphrase"

1

Liu, Xianggen, Wenqiang Lei, Jiancheng Lv et Jizhe Zhou. « Abstract Rule Learning for Paraphrase Generation ». Dans Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California : International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/593.

Texte intégral
Résumé :
In early years, paraphrase generation typically adopts rule-based methods, which are interpretable and able to make global transformations to the original sentence. But they struggle to produce fluent paraphrases. Recently, deep neural networks have shown impressive performances in generating paraphrases. However, the current neural models are black boxes and are prone to make local modifications to the inputs. In this work, we combine these two approaches into RULER, a novel approach that performs abstract rule learning for paraphrasing. The key idea is to explicitly learn generalizable rules that could enhance the paraphrase generation process of neural networks. In RULER, we first propose a rule generalizability metric to guide the model to generate rules underlying the paraphrasing. Then, we leverage neural networks to generate paraphrases by refining the sentences transformed by the learned rules. Extensive experimental results demonstrate the superiority of RULER over previous state-of-the-art methods in terms of paraphrase quality, generalization ability and interpretability.
Styles APA, Harvard, Vancouver, ISO, etc.
2

Liu, Mingtong, Erguang Yang, Deyi Xiong, Yujie Zhang, Chen Sheng, Changjian Hu, Jinan Xu et Yufeng Chen. « Exploring Bilingual Parallel Corpora for Syntactically Controllable Paraphrase Generation ». Dans Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. California : International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/547.

Texte intégral
Résumé :
Paraphrase generation is of great importance to many downstream tasks in natural language processing. Recent efforts have focused on generating paraphrases in specific syntactic forms, which, generally, heavily relies on manually annotated paraphrase data that is not easily available for many languages and domains. In this paper, we propose a novel end-to-end framework to leverage existing large-scale bilingual parallel corpora to generate paraphrases under the control of syntactic exemplars. In order to train one model over the two languages of parallel corpora, we embed sentences of them into the same content and style spaces with shared content and style encoders using cross-lingual word embeddings. We propose an adversarial discriminator to disentangle the content and style space, and employ a latent variable to model the syntactic style of a given exemplar in order to guide the two decoders for generation. Additionally, we introduce cycle and masking learning schemes to efficiently train the model. Experiments and analyses demonstrate that the proposed model trained only on bilingual parallel data is capable of generating diverse paraphrases with desirable syntactic styles. Fine-tuning the trained model on a small paraphrase corpus makes it substantially outperform state-of-the-art paraphrase generation models trained on a larger paraphrase dataset.
Styles APA, Harvard, Vancouver, ISO, etc.
3

Guo, Zilu, Zhongqiang Huang, Kenny Q. Zhu, Guandan Chen, Kaibo Zhang, Boxing Chen et Fei Huang. « Automatically Paraphrasing via Sentence Reconstruction and Round-trip Translation ». Dans Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}. California : International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/ijcai.2021/525.

Texte intégral
Résumé :
Paraphrase generation plays key roles in NLP tasks such as question answering, machine translation, and information retrieval. In this paper, we propose a novel framework for paraphrase generation. It simultaneously decodes the output sentence using a pretrained wordset-to-sequence model and a round-trip translation model. We evaluate this framework on Quora, WikiAnswers, MSCOCO and Twitter, and show its advantage over previous state-of-the-art unsupervised methods and distantly-supervised methods by significant margins on all datasets. For Quora and WikiAnswers, our framework even performs better than some strongly supervised methods with domain adaptation. Further, we show that the generated paraphrases can be used to augment the training data for machine translation to achieve substantial improvements.
Styles APA, Harvard, Vancouver, ISO, etc.
4

Jayawardena, Lasal, et Prasan Yapa. « Parafusion : A Large-Scale LLM-Driven English Paraphrase Dataset Infused with High-Quality Lexical and Syntactic Diversity ». Dans 5th International Conference on Artificial Intelligence and Big Data. Academy & Industry Research Collaboration Center, 2024. http://dx.doi.org/10.5121/csit.2024.140418.

Texte intégral
Résumé :
Paraphrase generation is a pivotal task in natural language processing (NLP). Existing datasets in the domain lack syntactic and lexical diversity, resulting in paraphrases that closely resemble the source sentences. Moreover, these datasets often contain hate speech and noise, and may unintentionally include non-English language sentences. This research introduces ParaFusion, a large-scale, high-quality English paraphrase dataset developed using Large Language Models (LLM) to address these challenges. ParaFusion augments existing datasets with high-quality data, significantly enhancing both lexical and syntactic diversity while maintaining close semantic similarity. It also mitigates the presence of hate speech and reduces noise, ensuring a cleaner and more focused English dataset. Results show that ParaFusion offers at least a 25% improvement in both syntactic and lexical diversity, measured across several metrics for each data source. The paper also aims to set a gold standard for paraphrase evaluation as it contains one of the most comprehensive evaluation strategies to date. The results underscore the potential of ParaFusion as a valuable resource for improving NLP applications.
Styles APA, Harvard, Vancouver, ISO, etc.
5

Shalamov, Viacheslav, Valeria Efimova et Andrey Filchenkov. « Paraphrase Quality Assessment Metric and Russian Paraphrase Dataset Collection ». Dans 2021 Ivannikov Ispras Open Conference (ISPRAS). IEEE, 2021. http://dx.doi.org/10.1109/ispras53967.2021.00025.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
6

Barzilay, Regina, et Lillian Lee. « Learning to paraphrase ». Dans the 2003 Conference of the North American Chapter of the Association for Computational Linguistics. Morristown, NJ, USA : Association for Computational Linguistics, 2003. http://dx.doi.org/10.3115/1073445.1073448.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
7

Yu, Boya, Konstantine Arkoudas et Wael Hamza. « Delexicalized Paraphrase Generation ». Dans Proceedings of the 28th International Conference on Computational Linguistics : Industry Track. Stroudsburg, PA, USA : International Committee on Computational Linguistics, 2020. http://dx.doi.org/10.18653/v1/2020.coling-industry.10.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
8

Yu, Boya, Konstantine Arkoudas et Wael Hamza. « Delexicalized Paraphrase Generation ». Dans Proceedings of the 28th International Conference on Computational Linguistics : Industry Track. Stroudsburg, PA, USA : International Committee on Computational Linguistics, 2020. http://dx.doi.org/10.18653/v1/2020.coling-industry.10.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
9

Nayak, Kota Shamanth Ramanath, et Leila Kosseim. « Analyzing Persuasive Strategies in Meme Texts : A Fusion of Language Models with Paraphrase Enrichment ». Dans 12th International Conference of Security, Privacy and Trust Management. Academy & Industry Research Collaboration Center, 2024. http://dx.doi.org/10.5121/csit.2024.141113.

Texte intégral
Résumé :
This paper describes our approach to hierarchical multi-label detection of persuasion techniques in meme texts. Our model, developed as a part of the recent SemEval task, is based on fine-tuning individual language models (BERT, XLM-RoBERTa, and mBERT) and leveraging a mean-based ensemble model in addition to dataset augmentation through paraphrase generation from ChatGPT. The scope of the study encompasses enhancing model performance through innovative training techniques and data augmentation strategies. The problem addressed is the effective identification and classification of multiple persuasive techniques in meme texts, a task complicated by the diversity and complexity of such content. The objective of the paper is to improve detection accuracy by refining model training methods and examining the impact of balanced versus unbalanced training datasets. Novelty in the results and discussion lies in the finding that training with paraphrases enhances model performance, yet a balanced training set proves more advantageous than a larger unbalanced one. Additionally, the analysis reveals the potential pitfalls of indiscriminate incorporation of paraphrases from diverse distributions, which can introduce substantial noise. Results with the SemEval 2024 data confirm these insights, demonstrating improved model efficacy with the proposed methods.
Styles APA, Harvard, Vancouver, ISO, etc.
10

Dong, Qingxiu, Xiaojun Wan et Yue Cao. « ParaSCI : A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation ». Dans Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics : Main Volume. Stroudsburg, PA, USA : Association for Computational Linguistics, 2021. http://dx.doi.org/10.18653/v1/2021.eacl-main.33.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.

Rapports d'organisations sur le sujet "Paraphrase"

1

Shinyama, Yusuke, et Satoshi Sekine. Paraphrase Acquisition for Information Extraction. Fort Belvoir, VA : Defense Technical Information Center, janvier 2003. http://dx.doi.org/10.21236/ada460236.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
2

Russo-Lassner, Grazia, Jimmy Lin et Philip Resnik. A Paraphrase-Based Approach to Machine Translation Evaluation. Fort Belvoir, VA : Defense Technical Information Center, août 2005. http://dx.doi.org/10.21236/ada448032.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
3

MacLaughlin, Dawn M. Parrot : The Janus Paraphraser. Fort Belvoir, VA : Defense Technical Information Center, septembre 1989. http://dx.doi.org/10.21236/ada214588.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
4

Ibrahim, Ali, Boris Katz et Jimmy Lin. Extracting Structural Paraphrases from Aligned Monolingual Corpora. Fort Belvoir, VA : Defense Technical Information Center, janvier 2003. http://dx.doi.org/10.21236/ada460577.

Texte intégral
Styles APA, Harvard, Vancouver, ISO, etc.
5

Yatsymirska, Mariya. SOCIAL EXPRESSION IN MULTIMEDIA TEXTS. Ivan Franko National University of Lviv, février 2021. http://dx.doi.org/10.30970/vjo.2021.49.11072.

Texte intégral
Résumé :
The article investigates functional techniques of extralinguistic expression in multimedia texts; the effectiveness of figurative expressions as a reaction to modern events in Ukraine and their influence on the formation of public opinion is shown. Publications of journalists, broadcasts of media resonators, experts, public figures, politicians, readers are analyzed. The language of the media plays a key role in shaping the worldview of the young political elite in the first place. The essence of each statement is a focused thought that reacts to events in the world or in one’s own country. The most popular platform for mass information and social interaction is, first of all, network journalism, which is characterized by mobility and unlimited time and space. Authors have complete freedom to express their views in direct language, including their own word formation. Phonetic, lexical, phraseological and stylistic means of speech create expression of the text. A figurative word, a good aphorism or proverb, a paraphrased expression, etc. enhance the effectiveness of a multimedia text. This is especially important for headlines that simultaneously inform and influence the views of millions of readers. Given the wide range of issues raised by the Internet as a medium, research in this area is interdisciplinary. The science of information, combining language and social communication, is at the forefront of global interactions. The Internet is an effective source of knowledge and a forum for free thought. Nonlinear texts (hypertexts) – «branching texts or texts that perform actions on request», multimedia texts change the principles of information collection, storage and dissemination, involving billions of readers in the discussion of global issues. Mastering the word is not an easy task if the author of the publication is not well-read, is not deep in the topic, does not know the psychology of the audience for which he writes. Therefore, the study of media broadcasting is an important component of the professional training of future journalists. The functions of the language of the media require the authors to make the right statements and convincing arguments in the text. Journalism education is not only knowledge of imperative and dispositive norms, but also apodictic ones. In practice, this means that there are rules in media creativity that are based on logical necessity. Apodicticity is the first sign of impressive language on the platform of print or electronic media. Social expression is a combination of creative abilities and linguistic competencies that a journalist realizes in his activity. Creative self-expression is realized in a set of many important factors in the media: the choice of topic, convincing arguments, logical presentation of ideas and deep philological education. Linguistic art, in contrast to painting, music, sculpture, accumulates all visual, auditory, tactile and empathic sensations in a universal sign – the word. The choice of the word for the reproduction of sensory and semantic meanings, its competent use in the appropriate context distinguishes the journalist-intellectual from other participants in forums, round tables, analytical or entertainment programs. Expressive speech in the media is a product of the intellect (ability to think) of all those who write on socio-political or economic topics. In the same plane with him – intelligence (awareness, prudence), the first sign of which (according to Ivan Ogienko) is a good knowledge of the language. Intellectual language is an important means of organizing a journalistic text. It, on the one hand, logically conveys the author’s thoughts, and on the other – encourages the reader to reflect and comprehend what is read. The richness of language is accumulated through continuous self-education and interesting communication. Studies of social expression as an important factor influencing the formation of public consciousness should open up new facets of rational and emotional media broadcasting; to trace physical and psychological reactions to communicative mimicry in the media. Speech mimicry as one of the methods of disguise is increasingly becoming a dangerous factor in manipulating the media. Mimicry is an unprincipled adaptation to the surrounding social conditions; one of the most famous examples of an animal characterized by mimicry (change of protective color and shape) is a chameleon. In a figurative sense, chameleons are called adaptive journalists. Observations show that mimicry in politics is to some extent a kind of game that, like every game, is always conditional and artificial.
Styles APA, Harvard, Vancouver, ISO, etc.
Nous offrons des réductions sur tous les plans premium pour les auteurs dont les œuvres sont incluses dans des sélections littéraires thématiques. Contactez-nous pour obtenir un code promo unique!

Vers la bibliographie
Current page language: French.
You might want to see the page in this language: English.
Change language