Relevant bibliographies by topics / Neural language models

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Books
  4. Book chapters
  5. Conference papers
  6. Reports

Academic literature on the topic 'Neural language models'

Author: Grafiati
Published: 25 May 2024
Last updated: 22 June 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Neural language models.'

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.

Journal articles on the topic "Neural language models"

1

Buckman, Jacob, and Graham Neubig. "Neural Lattice Language Models." Transactions of the Association for Computational Linguistics 6 (December 2018): 529–41. http://dx.doi.org/10.1162/tacl_a_00036.

Full text
Abstract:
In this work, we propose a new language modeling paradigm that has the ability to perform both prediction and moderation of information flow at multiple granularities: neural lattice language models. These models construct a lattice of possible paths through a sentence and marginalize across this lattice to calculate sequence probabilities or optimize parameters. This approach allows us to seamlessly incorporate linguistic intuitions — including polysemy and the existence of multiword lexical items — into our language model. Experiments on multiple language modeling tasks show that English neural lattice language models that utilize polysemous embeddings are able to improve perplexity by 9.95% relative to a word-level baseline, and that a Chinese model that handles multi-character tokens is able to improve perplexity by 20.94% relative to a character-level baseline.
APA, Harvard, Vancouver, ISO, and other styles
2

Bengio, Yoshua. "Neural net language models." Scholarpedia 3, no. 1 (2008): 3881. http://dx.doi.org/10.4249/scholarpedia.3881.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Dong, Li. "Learning natural language interfaces with neural models." AI Matters 7, no. 2 (2021): 14–17. http://dx.doi.org/10.1145/3478369.3478375.

Full text
Abstract:
Language is the primary and most natural means of communication for humans. The learning curve of interacting with various services (e.g., digital assistants, and smart appliances) would be greatly reduced if we could talk to machines using human language. However, in most cases computers can only interpret and execute formal languages.
APA, Harvard, Vancouver, ISO, and other styles
4

De Coster, Mathieu, and Joni Dambre. "Leveraging Frozen Pretrained Written Language Models for Neural Sign Language Translation." Information 13, no. 5 (2022): 220. http://dx.doi.org/10.3390/info13050220.

Full text
Abstract:
We consider neural sign language translation: machine translation from signed to written languages using encoder–decoder neural networks. Translating sign language videos to written language text is especially complex because of the difference in modality between source and target language and, consequently, the required video processing. At the same time, sign languages are low-resource languages, their datasets dwarfed by those available for written languages. Recent advances in written language processing and success stories of transfer learning raise the question of how pretrained written language models can be leveraged to improve sign language translation. We apply the Frozen Pretrained Transformer (FPT) technique to initialize the encoder, decoder, or both, of a sign language translation model with parts of a pretrained written language model. We observe that the attention patterns transfer in zero-shot to the different modality and, in some experiments, we obtain higher scores (from 18.85 to 21.39 BLEU-4). Especially when gloss annotations are unavailable, FPTs can increase performance on unseen data. However, current models appear to be limited primarily by data quality and only then by data quantity, limiting potential gains with FPTs. Therefore, in further research, we will focus on improving the representations used as inputs to translation models.
APA, Harvard, Vancouver, ISO, and other styles
5

Mandy Lau. "Artificial intelligence language models and the false fantasy of participatory language policies." Working papers in Applied Linguistics and Linguistics at York 1 (September 13, 2021): 4–15. http://dx.doi.org/10.25071/2564-2855.5.

Full text
Abstract:
Artificial intelligence neural language models learn from a corpus of online language data, often drawn directly from user-generated content through crowdsourcing or the gift economy, bypassing traditional keepers of language policy and planning (such as governments and institutions). Here lies the dream that the languages of the digital world can bend towards individual needs and wants, and not the traditional way around. Through the participatory language work of users, linguistic diversity, accessibility, personalization, and inclusion can be increased. However, the promise of a more participatory, just, and emancipatory language policy as a result of neural language models is a false fantasy. I argue that neural language models represent a covert and oppressive form of language policy that benefits the privileged and harms the marginalized. Here, I examine the ideology underpinning neural language models and investigate the harms that result from these emerging subversive regulatory bodies.
APA, Harvard, Vancouver, ISO, and other styles
6

Chang, Tyler A., and Benjamin K. Bergen. "Word Acquisition in Neural Language Models." Transactions of the Association for Computational Linguistics 10 (2022): 1–16. http://dx.doi.org/10.1162/tacl_a_00444.

Full text
Abstract:
Abstract We investigate how neural language models acquire individual words during training, extracting learning curves and ages of acquisition for over 600 words on the MacArthur-Bates Communicative Development Inventory (Fenson et al., 2007). Drawing on studies of word acquisition in children, we evaluate multiple predictors for words’ ages of acquisition in LSTMs, BERT, and GPT-2. We find that the effects of concreteness, word length, and lexical class are pointedly different in children and language models, reinforcing the importance of interaction and sensorimotor experience in child language acquisition. Language models rely far more on word frequency than children, but, like children, they exhibit slower learning of words in longer utterances. Interestingly, models follow consistent patterns during training for both unidirectional and bidirectional models, and for both LSTM and Transformer architectures. Models predict based on unigram token frequencies early in training, before transitioning loosely to bigram probabilities, eventually converging on more nuanced predictions. These results shed light on the role of distributional learning mechanisms in children, while also providing insights for more human-like language acquisition in language models.
APA, Harvard, Vancouver, ISO, and other styles
7

Mezzoudj, Freha, and Abdelkader Benyettou. "An empirical study of statistical language models: n-gram language models vs. neural network language models." International Journal of Innovative Computing and Applications 9, no. 4 (2018): 189. http://dx.doi.org/10.1504/ijica.2018.095762.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Mezzoudj, Freha, and Abdelkader Benyettou. "An empirical study of statistical language models: n-gram language models vs. neural network language models." International Journal of Innovative Computing and Applications 9, no. 4 (2018): 189. http://dx.doi.org/10.1504/ijica.2018.10016827.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Qi, Kunxun, and Jianfeng Du. "Translation-Based Matching Adversarial Network for Cross-Lingual Natural Language Inference." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (2020): 8632–39. http://dx.doi.org/10.1609/aaai.v34i05.6387.

Full text
Abstract:
Cross-lingual natural language inference is a fundamental task in cross-lingual natural language understanding, widely addressed by neural models recently. Existing neural model based methods either align sentence embeddings between source and target languages, heavily relying on annotated parallel corpora, or exploit pre-trained cross-lingual language models that are fine-tuned on a single language and hard to transfer knowledge to another language. To resolve these limitations in existing methods, this paper proposes an adversarial training framework to enhance both pre-trained models and classical neural models for cross-lingual natural language inference. It trains on the union of data in the source language and data in the target language, learning language-invariant features to improve the inference performance. Experimental results on the XNLI benchmark demonstrate that three popular neural models enhanced by the proposed framework significantly outperform the original models.
APA, Harvard, Vancouver, ISO, and other styles
10

Angius, Nicola, Pietro Perconti, Alessio Plebe, and Alessandro Acciai. "The Simulative Role of Neural Language Models in Brain Language Processing." Philosophies 9, no. 5 (2024): 137. http://dx.doi.org/10.3390/philosophies9050137.

Full text
Abstract:
This paper provides an epistemological and methodological analysis of the recent practice of using neural language models to simulate brain language processing. It is argued that, on the one hand, this practice can be understood as an instance of the traditional simulative method in artificial intelligence, following a mechanistic understanding of the mind; on the other hand, that it modifies the simulative method significantly. Firstly, neural language models are introduced; a study case showing how neural language models are being applied in cognitive neuroscience for simulative purposes is then presented; after recalling the main epistemological features of the simulative method in artificial intelligence, it is finally highlighted how the epistemic opacity of neural language models is tackled by using the brain itself to simulate the neural language model and to test hypotheses about it, in what is called here a co-simulation.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "Neural language models"

1

Lei, Tao Ph D. Massachusetts Institute of Technology. "Interpretable neural models for natural language processing." Thesis, Massachusetts Institute of Technology, 2017. http://hdl.handle.net/1721.1/108990.

Full text
Abstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.<br>Cataloged from PDF version of thesis.<br>Includes bibliographical references (pages 109-119).<br>The success of neural network models often comes at a cost of interpretability. This thesis addresses the problem by providing justifications behind the model's structure and predictions. In the first part of this thesis, we present a class of sequence operations for text processing. The proposed component generalizes from convolution operations and gated aggregations. As justifications, we relate this component to string kernels, i.e. functions measuring the similarity between sequences, and demonstrate how it encodes the efficient kernel computing algorithm into its structure. The proposed model achieves state-of-the-art or competitive results compared to alternative architectures (such as LSTMs and CNNs) across several NLP applications. In the second part, we learn rationales behind the model's prediction by extracting input pieces as supporting evidence. Rationales are tailored to be short and coherent, yet sufficient for making the same prediction. Our approach combines two modular components, generator and encoder, which are trained to operate well together. The generator specifies a distribution over text fragments as candidate rationales and these are passed through the encoder for prediction. Rationales are never given during training. Instead, the model is regularized by the desiderata for rationales. We demonstrate the effectiveness of this learning framework in applications such multi-aspect sentiment analysis. Our method achieves a performance over 90% evaluated against manual annotated rationales.<br>by Tao Lei.<br>Ph. D.
APA, Harvard, Vancouver, ISO, and other styles
2

Kunz, Jenny. "Neural Language Models with Explicit Coreference Decision." Thesis, Uppsala universitet, Institutionen för lingvistik och filologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-371827.

Full text
Abstract:
Coreference is an important and frequent concept in any form of discourse, and Coreference Resolution (CR) a widely used task in Natural Language Understanding (NLU). In this thesis, we implement and explore two recent models that include the concept of coreference in Recurrent Neural Network (RNN)-based Language Models (LM). Entity and reference decisions are modeled explicitly in these models using attention mechanisms. Both models learn to save the previously observed entities in a set and to decide if the next token created by the LM is a mention of one of the entities in the set, an entity that has not been observed yet, or not an entity. After a theoretical analysis where we compare the two LMs to each other and to a state of the art Coreference Resolution system, we perform an extensive quantitative and qualitative analysis. For this purpose, we train the two models and a classical RNN-LM as the baseline model on the OntoNotes 5.0 corpus with coreference annotation. While we do not reach the baseline in the perplexity metric, we show that the models’ relative performance on entity tokens has the potential to improve when including the explicit entity modeling. We show that the most challenging point in the systems is the decision if the next token is an entity token, while the decision which entity the next token refers to performs comparatively well. Our analysis in the context of a text generation task shows that a wide-spread error source for the mention creation process is the confusion of tokens that refer to related but different entities in the real world, presumably a result of the context-based word representations in the models. Our re-implementation of the DeepMind model by Yang et al. 2016 performs notably better than the re-implementation of the EntityNLM model by Ji et al. 2017 with a perplexity of 107 compared to a perplexity of 131.
APA, Harvard, Vancouver, ISO, and other styles
3

Labeau, Matthieu. "Neural language models : Dealing with large vocabularies." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLS313/document.

Full text
Abstract:
Le travail présenté dans cette thèse explore les méthodes pratiques utilisées pour faciliter l'entraînement et améliorer les performances des modèles de langues munis de très grands vocabulaires. La principale limite à l'utilisation des modèles de langue neuronaux est leur coût computationnel: il dépend de la taille du vocabulaire avec laquelle il grandit linéairement. La façon la plus aisée de réduire le temps de calcul de ces modèles reste de limiter la taille du vocabulaire, ce qui est loin d'être satisfaisant pour de nombreuses tâches. La plupart des méthodes existantes pour l'entraînement de ces modèles à grand vocabulaire évitent le calcul de la fonction de partition, qui est utilisée pour forcer la distribution de sortie du modèle à être normalisée en une distribution de probabilités. Ici, nous nous concentrons sur les méthodes à base d'échantillonnage, dont le sampling par importance et l'estimation contrastive bruitée. Ces méthodes permettent de calculer facilement une approximation de cette fonction de partition. L'examen des mécanismes de l'estimation contrastive bruitée nous permet de proposer des solutions qui vont considérablement faciliter l'entraînement, ce que nous montrons expérimentalement. Ensuite, nous utilisons la généralisation d'un ensemble d'objectifs basés sur l'échantillonnage comme divergences de Bregman pour expérimenter avec de nouvelles fonctions objectif. Enfin, nous exploitons les informations données par les unités sous-mots pour enrichir les représentations en sortie du modèle. Nous expérimentons avec différentes architectures, sur le Tchèque, et montrons que les représentations basées sur les caractères permettent l'amélioration des résultats, d'autant plus lorsque l'on réduit conjointement l'utilisation des représentations de mots<br>This work investigates practical methods to ease training and improve performances of neural language models with large vocabularies. The main limitation of neural language models is their expensive computational cost: it depends on the size of the vocabulary, with which it grows linearly. Despite several training tricks, the most straightforward way to limit computation time is to limit the vocabulary size, which is not a satisfactory solution for numerous tasks. Most of the existing methods used to train large-vocabulary language models revolve around avoiding the computation of the partition function, ensuring that output scores are normalized into a probability distribution. Here, we focus on sampling-based approaches, including importance sampling and noise contrastive estimation. These methods allow an approximate computation of the partition function. After examining the mechanism of self-normalization in noise-contrastive estimation, we first propose to improve its efficiency with solutions that are adapted to the inner workings of the method and experimentally show that they considerably ease training. Our second contribution is to expand on a generalization of several sampling based objectives as Bregman divergences, in order to experiment with new objectives. We use Beta divergences to derive a set of objectives from which noise contrastive estimation is a particular case. Finally, we aim at improving performances on full vocabulary language models, by augmenting output words representation with subwords. We experiment on a Czech dataset and show that using character-based representations besides word embeddings for output representations gives better results. We also show that reducing the size of the output look-up table improves results even more
APA, Harvard, Vancouver, ISO, and other styles
4

Bayer, Ali Orkan. "Semantic Language models with deep neural Networks." Doctoral thesis, Università degli studi di Trento, 2015. https://hdl.handle.net/11572/367784.

Full text
Abstract:
Spoken language systems (SLS) communicate with users in natural language through speech. There are two main problems related to processing the spoken input in SLS. The first one is automatic speech recognition (ASR) which recognizes what the user says. The second one is spoken language understanding (SLU) which understands what the user means. We focus on the language model (LM) component of SLS. LMs constrain the search space that is used in the search for the best hypothesis. Therefore, they play a crucial role in the performance of SLS. It has long been discussed that an improvement in the recognition performance does not necessarily yield a better understanding performance. Therefore, optimization of LMs for the understanding performance is crucial. In addition, long-range dependencies in languages are hard to handle with statistical language models. These two problems are addressed in this thesis. We investigate two different LM structures. The first LM that we investigate enable SLS to understand better what they recognize by searching the ASR hypotheses for the best understanding performance. We refer to these models as joint LMs. They use lexical and semantic units jointly in the LM. The second LM structure uses the semantic context of an utterance, which can also be described as “what the system understands†, to search for a better hypothesis that improves the recognition and the understanding performance. We refer to these models as semantic LMs (SELMs). SELMs use features that are based on a well established theory of lexical semantics, namely the theory of frame semantics. They incorporate the semantic features which are extracted from the ASR hypothesis into the LM and handle long-range dependencies by using the semantic relationships between words and semantic context. ASR noise is propagated to the semantic features, to suppress this noise we introduce the use of deep semantic encodings for semantic feature extraction. In this way, SELMs optimize both the recognition and the understanding performance.
APA, Harvard, Vancouver, ISO, and other styles
5

Bayer, Ali Orkan. "Semantic Language models with deep neural Networks." Doctoral thesis, University of Trento, 2015. http://eprints-phd.biblio.unitn.it/1578/1/bayer_thesis.pdf.

Full text
Abstract:
Spoken language systems (SLS) communicate with users in natural language through speech. There are two main problems related to processing the spoken input in SLS. The first one is automatic speech recognition (ASR) which recognizes what the user says. The second one is spoken language understanding (SLU) which understands what the user means. We focus on the language model (LM) component of SLS. LMs constrain the search space that is used in the search for the best hypothesis. Therefore, they play a crucial role in the performance of SLS. It has long been discussed that an improvement in the recognition performance does not necessarily yield a better understanding performance. Therefore, optimization of LMs for the understanding performance is crucial. In addition, long-range dependencies in languages are hard to handle with statistical language models. These two problems are addressed in this thesis. We investigate two different LM structures. The first LM that we investigate enable SLS to understand better what they recognize by searching the ASR hypotheses for the best understanding performance. We refer to these models as joint LMs. They use lexical and semantic units jointly in the LM. The second LM structure uses the semantic context of an utterance, which can also be described as “what the system understands”, to search for a better hypothesis that improves the recognition and the understanding performance. We refer to these models as semantic LMs (SELMs). SELMs use features that are based on a well established theory of lexical semantics, namely the theory of frame semantics. They incorporate the semantic features which are extracted from the ASR hypothesis into the LM and handle long-range dependencies by using the semantic relationships between words and semantic context. ASR noise is propagated to the semantic features, to suppress this noise we introduce the use of deep semantic encodings for semantic feature extraction. In this way, SELMs optimize both the recognition and the understanding performance.
APA, Harvard, Vancouver, ISO, and other styles
6

Li, Zhongliang. "Slim Embedding Layers for Recurrent Neural Language Models." Wright State University / OhioLINK, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=wright1531950458646138.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Gangireddy, Siva Reddy. "Recurrent neural network language models for automatic speech recognition." Thesis, University of Edinburgh, 2017. http://hdl.handle.net/1842/28990.

Full text
Abstract:
The goal of this thesis is to advance the use of recurrent neural network language models (RNNLMs) for large vocabulary continuous speech recognition (LVCSR). RNNLMs are currently state-of-the-art and shown to consistently reduce the word error rates (WERs) of LVCSR tasks when compared to other language models. In this thesis we propose various advances to RNNLMs. The advances are: improved learning procedures for RNNLMs, enhancing the context, and adaptation of RNNLMs. We learned better parameters by a novel pre-training approach and enhanced the context using prosody and syntactic features. We present a pre-training method for RNNLMs, in which the output weights of a feed-forward neural network language model (NNLM) are shared with the RNNLM. This is accomplished by first fine-tuning the weights of the NNLM, which are then used to initialise the output weights of an RNNLM with the same number of hidden units. To investigate the effectiveness of the proposed pre-training method, we have carried out text-based experiments on the Penn Treebank Wall Street Journal data, and ASR experiments on the TED lectures data. Across the experiments, we observe small but significant improvements in perplexity (PPL) and ASR WER. Next, we present unsupervised adaptation of RNNLMs. We adapted the RNNLMs to a target domain (topic or genre or television programme (show)) at test time using ASR transcripts from first pass recognition. We investigated two approaches to adapt the RNNLMs. In the first approach the forward propagating hidden activations are scaled - learning hidden unit contributions (LHUC). In the second approach we adapt all parameters of RNNLM.We evaluated the adapted RNNLMs by showing the WERs on multi genre broadcast speech data. We observe small (on an average 0.1% absolute) but significant improvements in WER compared to a strong unadapted RNNLM model. Finally, we present the context-enhancement of RNNLMs using prosody and syntactic features. The prosody features were computed from the acoustics of the context words and the syntactic features were from the surface form of the words in the context. We trained the RNNLMs with word duration, pause duration, final phone duration, syllable duration, syllable F0, part-of-speech tag and Combinatory Categorial Grammar (CCG) supertag features. The proposed context-enhanced RNNLMs were evaluated by reporting PPL and WER on two speech recognition tasks, Switchboard and TED lectures. We observed substantial improvements in PPL (5% to 15% relative) and small but significant improvements in WER (0.1% to 0.5% absolute).
APA, Harvard, Vancouver, ISO, and other styles
8

Scarcella, Alessandro. "Recurrent neural network language models in the context of under-resourced South African languages." Master's thesis, University of Cape Town, 2018. http://hdl.handle.net/11427/29431.

Full text
Abstract:
Over the past five years neural network models have been successful across a range of computational linguistic tasks. However, these triumphs have been concentrated in languages with significant resources such as large datasets. Thus, many languages, which are commonly referred to as under-resourced languages, have received little attention and have yet to benefit from recent advances. This investigation aims to evaluate the implications of recent advances in neural network language modelling techniques for under-resourced South African languages. Rudimentary, single layered recurrent neural networks (RNN) were used to model four South African text corpora. The accuracy of these models were compared directly to legacy approaches. A suite of hybrid models was then tested. Across all four datasets, neural networks led to overall better performing language models either directly or as part of a hybrid model. A short examination of punctuation marks in text data revealed that performance metrics for language models are greatly overestimated when punctuation marks have not been excluded. The investigation concludes by appraising the sensitivity of RNN language models (RNNLMs) to the size of the datasets by artificially constraining the datasets and evaluating the accuracy of the models. It is recommended that future research endeavours within this domain are directed towards evaluating more sophisticated RNNLMs as well as measuring their impact on application focused tasks such as speech recognition and machine translation.
APA, Harvard, Vancouver, ISO, and other styles
9

Le, Hai Son. "Continuous space models with neural networks in natural language processing." Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00776704.

Full text
Abstract:
The purpose of language models is in general to capture and to model regularities of language, thereby capturing morphological, syntactical and distributional properties of word sequences in a given language. They play an important role in many successful applications of Natural Language Processing, such as Automatic Speech Recognition, Machine Translation and Information Extraction. The most successful approaches to date are based on n-gram assumption and the adjustment of statistics from the training data by applying smoothing and back-off techniques, notably Kneser-Ney technique, introduced twenty years ago. In this way, language models predict a word based on its n-1 previous words. In spite of their prevalence, conventional n-gram based language models still suffer from several limitations that could be intuitively overcome by consulting human expert knowledge. One critical limitation is that, ignoring all linguistic properties, they treat each word as one discrete symbol with no relation with the others. Another point is that, even with a huge amount of data, the data sparsity issue always has an important impact, so the optimal value of n in the n-gram assumption is often 4 or 5 which is insufficient in practice. This kind of model is constructed based on the count of n-grams in training data. Therefore, the pertinence of these models is conditioned only on the characteristics of the training text (its quantity, its representation of the content in terms of theme, date). Recently, one of the most successful attempts that tries to directly learn word similarities is to use distributed word representations in language modeling, where distributionally words, which have semantic and syntactic similarities, are expected to be represented as neighbors in a continuous space. These representations and the associated objective function (the likelihood of the training data) are jointly learned using a multi-layer neural network architecture. In this way, word similarities are learned automatically. This approach has shown significant and consistent improvements when applied to automatic speech recognition and statistical machine translation tasks. A major difficulty with the continuous space neural network based approach remains the computational burden, which does not scale well to the massive corpora that are nowadays available. For this reason, the first contribution of this dissertation is the definition of a neural architecture based on a tree representation of the output vocabulary, namely Structured OUtput Layer (SOUL), which makes them well suited for large scale frameworks. The SOUL model combines the neural network approach with the class-based approach. It achieves significant improvements on both state-of-the-art large scale automatic speech recognition and statistical machine translations tasks. The second contribution is to provide several insightful analyses on their performances, their pros and cons, their induced word space representation. Finally, the third contribution is the successful adoption of the continuous space neural network into a machine translation framework. New translation models are proposed and reported to achieve significant improvements over state-of-the-art baseline systems.
APA, Harvard, Vancouver, ISO, and other styles
10

Miao, Yishu. "Deep generative models for natural language processing." Thesis, University of Oxford, 2017. http://ora.ox.ac.uk/objects/uuid:e4e1f1f9-e507-4754-a0ab-0246f1e1e258.

Full text
Abstract:
Deep generative models are essential to Natural Language Processing (NLP) due to their outstanding ability to use unlabelled data, to incorporate abundant linguistic features, and to learn interpretable dependencies among data. As the structure becomes deeper and more complex, having an effective and efficient inference method becomes increasingly important. In this thesis, neural variational inference is applied to carry out inference for deep generative models. While traditional variational methods derive an analytic approximation for the intractable distributions over latent variables, here we construct an inference network conditioned on the discrete text input to provide the variational distribution. The powerful neural networks are able to approximate complicated non-linear distributions and grant the possibilities for more interesting and complicated generative models. Therefore, we develop the potential of neural variational inference and apply it to a variety of models for NLP with continuous or discrete latent variables. This thesis is divided into three parts. Part I introduces a <b>generic variational inference framework</b> for generative and conditional models of text. For continuous or discrete latent variables, we apply a continuous reparameterisation trick or the REINFORCE algorithm to build low-variance gradient estimators. To further explore Bayesian non-parametrics in deep neural networks, we propose a family of neural networks that parameterise categorical distributions with continuous latent variables. Using the stick-breaking construction, an unbounded categorical distribution is incorporated into our deep generative models which can be optimised by stochastic gradient back-propagation with a continuous reparameterisation. Part II explores <b>continuous latent variable models for NLP</b>. Chapter 3 discusses the Neural Variational Document Model (NVDM): an unsupervised generative model of text which aims to extract a continuous semantic latent variable for each document. In Chapter 4, the neural topic models modify the neural document models by parameterising categorical distributions with continuous latent variables, where the topics are explicitly modelled by discrete latent variables. The models are further extended to neural unbounded topic models with the help of stick-breaking construction, and a truncation-free variational inference method is proposed based on a Recurrent Stick-breaking construction (RSB). Chapter 5 describes the Neural Answer Selection Model (NASM) for learning a latent stochastic attention mechanism to model the semantics of question-answer pairs and predict their relatedness. Part III discusses <b>discrete latent variable models</b>. Chapter 6 introduces latent sentence compression models. The Auto-encoding Sentence Compression Model (ASC), as a discrete variational auto-encoder, generates a sentence by a sequence of discrete latent variables representing explicit words. The Forced Attention Sentence Compression Model (FSC) incorporates a combined pointer network biased towards the usage of words from source sentence, which significantly improves the performance when jointly trained with the ASC model in a semi-supervised learning fashion. Chapter 7 describes the Latent Intention Dialogue Models (LIDM) that employ a discrete latent variable to learn underlying dialogue intentions. Additionally, the latent intentions can be interpreted as actions guiding the generation of machine responses, which could be further refined autonomously by reinforcement learning. Finally, Chapter 8 summarizes our findings and directions for future work.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Books on the topic "Neural language models"

1

1957-, Houghton George, ed. Connectionist models in cognitive psychology. Psychology Press, 2004.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
2

Miikkulainen, Risto. Subsymbolic natural language processing: An integrated model of scripts, lexicon, and memory. MIT Press, 1993.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
3

Bavaeva, Ol'ga. Metaphorical parallels of the neutral nomination "man" in modern English. INFRA-M Academic Publishing LLC., 2022. http://dx.doi.org/10.12737/1858259.

Full text
Abstract:
The monograph is devoted to a multidimensional analysis of metaphor in modern English as a parallel nomination that exists along with a neutral equivalent denoting a person. The problem of determining the essence of metaphorical names and their role in the language has attracted the attention of many foreign and domestic linguists on the material of various languages, but until now the fact of the parallel existence of metaphors and neutral nominations has not been emphasized.&#x0D; The research is in line with modern problems of linguistics related to the relationship of language, thinking and reflection of the surrounding reality. All these problems are integrated and resolved within the framework of linguistic semantics, in particular in the semantics of metaphor. Multilevel study of language material based on semantic, component, etymological analysis methods contributed to a systematic and comprehensive description of this most important part of the lexical system of the English language.&#x0D; Metaphorical parallels are considered as the result of the interaction of three complexes, which allows us to identify their associative-figurative base, as well as the types of metaphorical parallels, depending on the nature of the connection between direct and figurative meaning. Based on the analysis of various human character traits and behavior that evoke associations with animals, birds, objects, zoomorphic, artifact, somatic, floral and anthropomorphic metaphorical parallels of the neutral nomination "man" are distinguished. The social aspect of metaphorical parallels is also investigated as a reflection of gender, status and age characteristics of a person.&#x0D; It can be used in the training of philologists and translators when reading theoretical courses on lexicology, stylistics, word formation of the English language, as well as in practical classes, in lexicographic practice.
APA, Harvard, Vancouver, ISO, and other styles
4

Arbib, Michael. Neural Models of Language Processes. Elsevier Science & Technology Books, 2012.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
5

Cairns, Paul, Joseph P. Levy, Dimitrios Bairaktaris, and John A. Bullinaria. Connectionist Models of Memory and Language. Taylor & Francis Group, 2015.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
6

Dimitoglou, George, and Ahmad Tafti. Artificial Intelligence: Machine Learning, Convolutional Neural Networks and Large Language Models. de Gruyter GmbH, Walter, 2024.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
7

Dimitoglou, George, and Ahmad Tafti. Artificial Intelligence: Machine Learning, Convolutional Neural Networks and Large Language Models. de Gruyter GmbH, Walter, 2024.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
8

Dimitoglou, George, and Ahmad Tafti. Artificial Intelligence: Machine Learning, Convolutional Neural Networks and Large Language Models. de Gruyter GmbH, Walter, 2024.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
9

Connectionist Models in Cognitive Psychology. Taylor & Francis Group, 2014.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
10

Houghton, George. Connectionist Models in Cognitive Psychology. Taylor & Francis Group, 2004.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
More sources

Book chapters on the topic "Neural language models"

1

Skansi, Sandro. "Neural Language Models." In Undergraduate Topics in Computer Science. Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-319-73004-2_9.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Delasalles, Edouard, Sylvain Lamprier, and Ludovic Denoyer. "Dynamic Neural Language Models." In Neural Information Processing. Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-36718-3_24.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Kucharavy, Andrei. "From Deep Neural Language Models to LLMs." In Large Language Models in Cybersecurity. Springer Nature Switzerland, 2024. http://dx.doi.org/10.1007/978-3-031-54827-7_1.

Full text
Abstract:
AbstractLarge Language Models (LLMs) are scaled-up instances of Deep Neural Language Models—a type of Natural Language Processing (NLP) tools trained with Machine Learning (ML). To best understand how LLMs work, we must dive into what technologies they build on top of and what makes them different. To achieve this, an overview of the history of LLMs development, starting from the 1990s, is provided before covering the counterintuitive purely probabilistic nature of the Deep Neural Language Models, continuous token embedding spaces, recurrent neural networks-based models, what self-attention brought to the table, and finally, why scaling Deep Neural Language Models led to a qualitative change, warranting a new name for the technology.
APA, Harvard, Vancouver, ISO, and other styles
4

Hampton, Peter John, Hui Wang, and Zhiwei Lin. "Knowledge Transfer in Neural Language Models." In Artificial Intelligence XXXIV. Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-71078-5_12.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

O’Neill, James, and Danushka Bollegala. "Learning to Evaluate Neural Language Models." In Communications in Computer and Information Science. Springer Singapore, 2020. http://dx.doi.org/10.1007/978-981-15-6168-9_11.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Goldrick, Matthew. "Neural Network Models of Speech Production." In The Handbook of the Neuropsychology of Language. Wiley-Blackwell, 2012. http://dx.doi.org/10.1002/9781118432501.ch7.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

G, Santhosh Kumar. "Neural Language Models for (Fake?) News Generation." In Data Science for Fake News. Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-62696-9_6.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Huang, Yue, and Xiaodong Gu. "Temporal Modeling Approach for Video Action Recognition Based on Vision-language Models." In Neural Information Processing. Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-8067-3_38.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Shen, Tongtong, Longbiao Wang, Xie Chen, Kuntharrgyal Khysru, and Jianwu Dang. "Exploiting the Tibetan Radicals in Recurrent Neural Network for Low-Resource Language Models." In Neural Information Processing. Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-70096-0_28.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Goldberg, Yoav. "From Linear Models to Multi-layer Perceptrons." In Neural Network Methods for Natural Language Processing. Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-031-02165-7_3.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Neural language models"

1

Butoi, Alexandra, Ryan Cotterell, and Anej Svete. "Computational Expressivity of Neural Language Models." In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts). Association for Computational Linguistics, 2024. http://dx.doi.org/10.18653/v1/2024.acl-tutorials.3.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Cao, Yang, Yangsong Lan, Feiyan Zhai, and Piji Li. "5W1H Extraction With Large Language Models." In 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 2024. http://dx.doi.org/10.1109/ijcnn60899.2024.10651056.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Huang, Shubin, Qiong Wu, and Yiyi Zhou. "Adapting Pre-trained Language Models to Vision-Language Tasksvia Dynamic Visual Prompting." In 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 2024. http://dx.doi.org/10.1109/ijcnn60899.2024.10651317.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Hollinsworth, Oskar John, Curt Tigges, Atticus Geiger, and Neel Nanda. "Language Models Linearly Represent Sentiment." In Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP. Association for Computational Linguistics, 2024. http://dx.doi.org/10.18653/v1/2024.blackboxnlp-1.5.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Yang, Jiahong, Wenting Li, Haibo Cheng, and Ping Wang. "Targeted Password Guessing Using Neural Language Models." In ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2025. https://doi.org/10.1109/icassp49660.2025.10888919.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Peng, Yicui, Hao Chen, Ching-Sheng Lin, et al. "Uncertainty-Aware Explainable Recommendation with Large Language Models." In 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 2024. http://dx.doi.org/10.1109/ijcnn60899.2024.10651104.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Liu, Huijun, Bin Ji, Jie Yu, et al. "Offline Textual Adversarial Attacks against Large Language Models." In 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 2024. http://dx.doi.org/10.1109/ijcnn60899.2024.10650921.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Park, Hyunwook, Yifan Ding, Ling Zhang, et al. "High-speed Channel Simulator using Neural Language Models." In 2024 IEEE International Symposium on Electromagnetic Compatibility, Signal & Power Integrity (EMC+SIPI). IEEE, 2024. http://dx.doi.org/10.1109/emcsipi49824.2024.10705639.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

KP, Gouri, Visesh AV, Anoop V, Ashlin Parakkal, and Joman P. Joji. "Advancing Sign Language Prediction with Neural Network Models." In 2024 International Conference on Advancement in Renewable Energy and Intelligent Systems (AREIS). IEEE, 2024. https://doi.org/10.1109/areis62559.2024.10893631.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Mohammadi, Seyedali, Edward Raff, Jinendra Malekar, Vedant Palit, Francis Ferraro, and Manas Gaur. "WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions." In Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP. Association for Computational Linguistics, 2024. http://dx.doi.org/10.18653/v1/2024.blackboxnlp-1.23.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Reports on the topic "Neural language models"

1

Semerikov, Serhiy O., Illia O. Teplytskyi, Yuliia V. Yechkalo, and Arnold E. Kiv. Computer Simulation of Neural Networks Using Spreadsheets: The Dawn of the Age of Camelot. [б. в.], 2018. http://dx.doi.org/10.31812/123456789/2648.

Full text
Abstract:
The article substantiates the necessity to develop training methods of computer simulation of neural networks in the spreadsheet environment. The systematic review of their application to simulating artificial neural networks is performed. The authors distinguish basic approaches to solving the problem of network computer simulation training in the spreadsheet environment, joint application of spreadsheets and tools of neural network simulation, application of third-party add-ins to spreadsheets, development of macros using the embedded languages of spreadsheets; use of standard spreadsheet add-ins for non-linear optimization, creation of neural networks in the spreadsheet environment without add-ins and macros. After analyzing a collection of writings of 1890-1950, the research determines the role of the scientific journal “Bulletin of Mathematical Biophysics”, its founder Nicolas Rashevsky and the scientific community around the journal in creating and developing models and methods of computational neuroscience. There are identified psychophysical basics of creating neural networks, mathematical foundations of neural computing and methods of neuroengineering (image recognition, in particular). The role of Walter Pitts in combining the descriptive and quantitative theories of training is discussed. It is shown that to acquire neural simulation competences in the spreadsheet environment, one should master the models based on the historical and genetic approach. It is indicated that there are three groups of models, which are promising in terms of developing corresponding methods – the continuous two-factor model of Rashevsky, the discrete model of McCulloch and Pitts, and the discrete-continuous models of Householder and Landahl.
APA, Harvard, Vancouver, ISO, and other styles
2

Pasupuleti, Murali Krishna. Decentralized Creativity: AI-Infused Blockchain for Secure and Transparent Digital Innovation. National Education Services, 2025. https://doi.org/10.62311/nesx/rrvi125.

Full text
Abstract:
Abstract The convergence of artificial intelligence (AI) and blockchain technology is transforming the creative economy by enabling secure, transparent, and decentralized innovation in digital content creation, intellectual property management, and monetization. Traditional creative industries are often constrained by centralized platforms, opaque copyright enforcement, and unfair revenue distribution, which limit the autonomy and financial benefits of creators. By leveraging blockchain’s immutable ledger, smart contracts, and non-fungible tokens (NFTs), digital assets can be authenticated, tokenized, and securely traded, ensuring ownership verification and automated royalty distribution. Simultaneously, AI-driven tools such as generative adversarial networks (GANs), neural networks, and natural language processing (NLP) models facilitate content generation, curation, and adaptive recommendations, enhancing creative workflows and fostering new artistic possibilities. This research report explores the synergies between AI and blockchain in the decentralized creative economy, analyzing their impact on digital rights protection, NFT marketplaces, decentralized publishing, AI-assisted music composition, and smart licensing models. Furthermore, it examines regulatory challenges, ethical considerations, and scalability limitations that need to be addressed for mainstream adoption. By integrating AI-powered automation with blockchain’s decentralized infrastructure, this study outlines a sustainable roadmap for secure, fair, and transparent digital creativity in the Web3 era. Keywords AI-powered creativity, blockchain-based digital ownership, decentralized innovation, generative AI, smart contracts, non-fungible tokens (NFTs), digital content authentication, AI-driven content generation, decentralized autonomous organizations (DAOs), intellectual property management, AI in art and music, Web3 creativity, tokenized digital assets, secure content monetization, ethical AI in blockchain, AI-assisted copyright protection, decentralized publishing, AI-powered music composition, blockchain scalability, AI for digital rights management.
APA, Harvard, Vancouver, ISO, and other styles
3

Lee, Benjamin Yen Kit. Automated neuron explanation for code-trained language models. Iowa State University, 2024. http://dx.doi.org/10.31274/cc-20240624-267.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Apicella, M. L., J. Slaton, and B. Levi. Integrated Information Support System (IISS). Volume 5. Common Data Model Subsystem. Part 10. Neutral Data Manipulation Language (NDML) Precompiler Control Module Product Specification. Defense Technical Information Center, 1990. http://dx.doi.org/10.21236/ada250451.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Althoff, J. L., M. L. Apicella, and S. Singh. Integrated Information Support System (IISS). Volume 5. Common Data Model Subsystem. Part 5. Neutral Data Definition Language (NDDL) Development Specification. Defense Technical Information Center, 1990. http://dx.doi.org/10.21236/ada252450.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Apicella, M. L., J. Slaton, and B. Levi. Integrated Information Support System (IISS). Volume 5. Common Data Model Subsystem. Part 13. Neutral Data Manipulation Language (NDML) Precompiler Parse NDML Product Specification. Defense Technical Information Center, 1990. http://dx.doi.org/10.21236/ada250453.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Althoff, J., and M. Apicella. Integrated Information Support System (IISS). Volume 5. Common Data Model Subsystem. Part 9. Neutral Data Manipulation Language (NDML) Precompiler Development Specification. Section 2. Defense Technical Information Center, 1990. http://dx.doi.org/10.21236/ada252526.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Apicella, M. L., J. Slaton, and B. Levi. Integrated Information Support System (IISS). Volume 5. Common Data Model Subsystem. Part 12. Neutral Data Manipulation Language (NDML) Precompiler Parse Procedure Division Product Specification. Defense Technical Information Center, 1990. http://dx.doi.org/10.21236/ada250452.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Apicella, M. L., J. Slaton, B. Levi, and A. Pashak. Integrated Information Support System (IISS). Volume 5. Common Data Model Subsystem. Part 23. Neutral Data Manipulation Language (NDML) Precompiler Build Source Code Product Specification. Defense Technical Information Center, 1990. http://dx.doi.org/10.21236/ada250460.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Apicella, M. L., J. Slaton, B. Levi, and A. Pashak. Integrated Information Support System (IISS). Volume 5. Common Data Model Subsystem. Part 24. Neutral Data Manipulation Language (NDML) Precompiler Generator Support Routines Product Specification. Defense Technical Information Center, 1990. http://dx.doi.org/10.21236/ada250461.

Full text
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Neural language models' for particular source types:
Journal articles Dissertations / Theses Books
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography