{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modelling/papers/157","list_of":"/task/language-modelling","task":"Language Modelling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":157,"pages_in_order":177,"rows_per_page":100,"rows":[15601,15700],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modelling","prev":"/task/language-modelling/papers/156","next":"/task/language-modelling/papers/158","papers":[{"url":null,"slug":"language-model-bootstrapping-using-neural","title":"Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition","date":"2019-12-02","arxiv_id":"1912.00958","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-modelling-with-nmt-query-translation","title":"Language Modelling with NMT Query Translation for Amharic-Arabic Cross-Language Information Retrieval","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mixtape-breaking-the-softmax-bottleneck","title":"Mixtape: Breaking the Softmax Bottleneck Efficiently","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-text-classification-using-sub-word","title":"Robust Text Classification using Sub-Word Information in Input Word Representations.","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-german-verb-argument-structures","title":"Neural language modeling of free word order argument structure","date":"2019-11-30","arxiv_id":"1912.00239","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-iterative-polishing-framework-based-on","title":"An Iterative Polishing Framework based on Quality Aware Masked Language Model for Chinese Poetry Generation","date":"2019-11-29","arxiv_id":"1911.13182","repositories_listed":0,"syntology":null},{"url":null,"slug":"inducing-relational-knowledge-from-bert","title":"Inducing Relational Knowledge from BERT","date":"2019-11-28","arxiv_id":"1911.12753","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimum-bayes-risk-training-of-rnn-transducer","title":"Minimum Bayes Risk Training of RNN-Transducer for End-to-End Speech Recognition","date":"2019-11-28","arxiv_id":"1911.12487","repositories_listed":0,"syntology":null},{"url":null,"slug":"findings-of-the-2016-wmt-shared-task-on-cross-1","title":"Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction","date":"2019-11-27","arxiv_id":"1911.12091","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplebooks-long-term-dependency-book-dataset","title":"SimpleBooks: Long-term dependency book dataset with simplified English vocabulary for word-level language modeling","date":"2019-11-27","arxiv_id":"1911.12391","repositories_listed":0,"syntology":null},{"url":null,"slug":"taking-a-stance-on-fake-news-towards","title":"Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection","date":"2019-11-27","arxiv_id":"1911.11951","repositories_listed":0,"syntology":null},{"url":null,"slug":"relevance-promoting-language-model-for-short","title":"Relevance-Promoting Language Model for Short-Text Conversation","date":"2019-11-26","arxiv_id":"1911.11489","repositories_listed":0,"syntology":null},{"url":null,"slug":"independent-language-modeling-architecture","title":"Independent language modeling architecture for end-to-end ASR","date":"2019-11-25","arxiv_id":"1912.00863","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-of-language","title":"Unsupervised Domain Adaptation of Language Models for Reading Comprehension","date":"2019-11-25","arxiv_id":"1911.10768","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-eeg-based-continuous-speech","title":"Improving EEG based Continuous Speech Recognition","date":"2019-11-24","arxiv_id":"1911.11610","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-neural-networks-rnns-a-gentle","title":"Recurrent Neural Networks (RNNs): A gentle Introduction and Overview","date":"2019-11-23","arxiv_id":"1912.05911","repositories_listed":0,"syntology":null},{"url":null,"slug":"empirical-autopsy-of-deep-video-captioning","title":"Empirical Autopsy of Deep Video Captioning Frameworks","date":"2019-11-21","arxiv_id":"1911.09345","repositories_listed":0,"syntology":null},{"url":null,"slug":"paraphrasing-with-large-language-models-1","title":"Paraphrasing with Large Language Models","date":"2019-11-21","arxiv_id":"1911.09661","repositories_listed":0,"syntology":null},{"url":null,"slug":"thick-net-parallel-network-structure-for","title":"Thick-Net: Parallel Network Structure for Sequential Modeling","date":"2019-11-19","arxiv_id":"1911.08074","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-natural-question-answering-with-1","title":"Unsupervised Natural Question Answering with a Small Model","date":"2019-11-19","arxiv_id":"1911.08340","repositories_listed":0,"syntology":null},{"url":null,"slug":"drug-repurposing-for-cancer-an-nlp-approach","title":"Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies","date":"2019-11-18","arxiv_id":"1911.07819","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-zone-unit-for-recurrent-neural-networks","title":"Multi-Zone Unit for Recurrent Neural Networks","date":"2019-11-17","arxiv_id":"1911.07184","repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-as-decoder-trading-flexibility-1","title":"Classification as Decoder: Trading Flexibility for Control in Medical Dialogue","date":"2019-11-16","arxiv_id":"1911.08554","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-subword-level-language-model-for-bangla","title":"A Subword Level Language Model for Bangla Language","date":"2019-11-15","arxiv_id":"1911.07613","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-associative-memory-based-on-contextual","title":"Sparse associative memory based on contextual code learning for disambiguating word senses","date":"2019-11-14","arxiv_id":"1911.06415","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-a-code-switching-language-model-with","title":"Training a code-switching language model with monolingual data","date":"2019-11-14","arxiv_id":"1911.06003","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-and-evaluating-a-deep-learning","title":"Adapting and evaluating a deep learning language model for clinical why-question answering","date":"2019-11-13","arxiv_id":"1911.05604","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-sparsification-of-gated-recurrent","title":"Structured Sparsification of Gated Recurrent Neural Networks","date":"2019-11-13","arxiv_id":"1911.05585","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-span-language-modeling-for-speech","title":"Long-span language modeling for speech recognition","date":"2019-11-11","arxiv_id":"1911.04571","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-architecture-search-for-natural","title":"Neural Architecture Search for Natural Language Understanding","date":"2019-11-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rnn-test-adversarial-testing-framework-for","title":"RNN-Test: Towards Adversarial Testing for Recurrent Neural Network Systems","date":"2019-11-11","arxiv_id":"1911.06155","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-driven-unsupervised-neural","title":"Language Model-Driven Unsupervised Neural Machine Translation","date":"2019-11-10","arxiv_id":"1911.03937","repositories_listed":0,"syntology":null},{"url":null,"slug":"preventing-posterior-collapse-in-sequence","title":"On Posterior Collapse and Encoder Feature Dispersion in Sequence VAEs","date":"2019-11-10","arxiv_id":"1911.03976","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-mixed-to-monolingual-translation","title":"Code-Mixed to Monolingual Translation Framework","date":"2019-11-09","arxiv_id":"1911.03772","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-sentiment-bias-in-language-models-1","title":"Reducing Sentiment Bias in Language Models via Counterfactual Evaluation","date":"2019-11-08","arxiv_id":"1911.03064","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-lig-system-for-the-english-czech-text","title":"The LIG system for the English-Czech Text Translation Task of IWSLT 2019","date":"2019-11-07","arxiv_id":"1911.02898","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-answer-by-learning-to-ask-getting","title":"Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds","date":"2019-11-06","arxiv_id":"1911.02365","repositories_listed":0,"syntology":null},{"url":null,"slug":"rnn-t-for-latency-controlled-asr-with","title":"RNN-T For Latency Controlled ASR With Improved Beam Search","date":"2019-11-05","arxiv_id":"1911.01629","repositories_listed":0,"syntology":null},{"url":null,"slug":"bas-an-answer-selection-method-using-bert","title":"BAS: An Answer Selection Method Using BERT Language Model","date":"2019-11-04","arxiv_id":"1911.01528","repositories_listed":0,"syntology":null},{"url":null,"slug":"emerging-cross-lingual-structure-in","title":"Emerging Cross-lingual Structure in Pretrained Language Models","date":"2019-11-04","arxiv_id":"1911.01464","repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-cnn-a-hierarchical-patent-classifier","title":"BERT-CNN: a Hierarchical Patent Classifier Based on a Pre-Trained Language Model","date":"2019-11-03","arxiv_id":"1911.06241","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-and-effective-method-for-injecting","title":"A Simple and Effective Method for Injecting Word-Level Information into Character-Aware Neural Language Models","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-argument-quality-assessment-new-1","title":"Automatic Argument Quality Assessment - New Datasets and Methods","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"beamseg-a-joint-model-for-multi-document","title":"BeamSeg: A Joint Model for Multi-Document Segmentation and Topic Identification","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"chameleon-a-language-model-adaptation-toolkit","title":"Chameleon: A Language Model Adaptation Toolkit for Automatic Speech Recognition of Conversational Speech","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"character-based-models-for-adversarial-phone","title":"Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-top-down-and-bottom-up-neural","title":"Comparing Top-Down and Bottom-Up Neural Generative Dependency Models","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-neural-machine-translation-2","title":"Context-Aware Neural Machine Translation Decoding","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-text-denoising-with-masked-1","title":"Contextual Text Denoising with Masked Language Model","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coreference-resolution-in-full-text-articles","title":"Coreference Resolution in Full Text Articles with BERT and Syntax-based Mention Filtering","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-transfer-learning-with-data","title":"Cross-lingual Transfer Learning with Data Selection for Large-Scale Spoken Language Understanding","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-bidirectional-transformers-for-relation-1","title":"Deep Bidirectional Transformers for Relation Extraction without Supervision","date":"2019-11-01","arxiv_id":"1911.00313","repositories_listed":0,"syntology":null},{"url":null,"slug":"divisive-language-and-propaganda-detection","title":"Divisive Language and Propaganda Detection using Multi-head Attention Transformers with Deep Learning BERT-based Language Models for Binary Classification","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"english-myanmar-supervised-and-unsupervised","title":"English-Myanmar Supervised and Unsupervised NMT: NICT's Machine Translation Systems at WAT-2019","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-bert-for-lexical-normalization","title":"Enhancing BERT for Lexical Normalization","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-variational-autoencoders-with","title":"Enhancing Variational Autoencoders with Mutual Information Neural Estimation for Text Generation","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"experimenting-with-power-divergences-for","title":"Experimenting with Power Divergences for Language Modeling","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-propaganda-detection-with-fine","title":"Fine-Grained Propaganda Detection with Fine-Tuned BERT","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gem-generative-enhanced-model-for-adversarial","title":"GEM: Generative Enhanced Model for adversarial attacks","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-question-answering-system-with","title":"Generalizing Question Answering System with Pre-trained Language Model Fine-tuning","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hello-its-gpt-2-how-can-i-help-you-towards-1","title":"Hello, It's GPT-2 - How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/improving-multi-label-emotion-classification-1","slug":"improving-multi-label-emotion-classification-1","title":"Improving Multi-label Emotion Classification by Integrating both General and Domain-specific Knowledge","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-pre-trained-multilingual-model-with","title":"Improving Pre-Trained Multilingual Model with Vocabulary Expansion","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"jeff-da-at-coin-shared-task","title":"Jeff Da at COIN - Shared Task: BIG MOOD: Relating Transformers to Explicit Commonsense Knowledge","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"justifying-recommendations-using-distantly","title":"Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowsemlm-a-knowledge-infused-semantic","title":"KnowSemLM: A Knowledge Infused Semantic Language Model","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mulcode-a-multiplicative-multi-way-model-for","title":"MulCode: A Multiplicative Multi-way Model for Compressing Neural Language Model","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-for-natural-language","title":"Multi-task Learning for Natural Language Generation in Task-Oriented Dialogue","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phonetic-normalization-for-machine","title":"Phonetic Normalization for Machine Translation of User Generated Content","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-bert-on-domain-resources-for","title":"Pre-Training BERT on Domain Resources for Short Answer Grading","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"selecting-planning-and-rewriting-a-modular","title":"Selecting, Planning, and Rewriting: A Modular Approach for Data-to-Document Generation and Translation","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spelling-aware-construction-of-macaronic","title":"Spelling-Aware Construction of Macaronic Texts for Teaching Foreign-Language Vocabulary","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-propaganda-embeddings-to-train-a","title":"Synthetic Propaganda Embeddings To Train A Linear Projection","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tilm-neural-language-models-with-evolving","title":"TILM: Neural Language Models with Evolving Topical Influence","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-aspect-based-multi-document","title":"Unsupervised Aspect-Based Multi-Document Abstractive Summarization","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neural-document-language-modeling-framework","title":"A neural document language modeling framework for spoken document retrieval","date":"2019-10-31","arxiv_id":"1910.14286","repositories_listed":0,"syntology":null},{"url":null,"slug":"positional-attention-based-frame","title":"Positional Attention-based Frame Identification with BERT: A Deep Learning Approach to Target Disambiguation and Semantic Frame Selection","date":"2019-10-31","arxiv_id":"1910.14549","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-text-denoising-with-masked","title":"Contextual Text Denoising with Masked Language Models","date":"2019-10-30","arxiv_id":"1910.14080","repositories_listed":0,"syntology":null},{"url":null,"slug":"fill-in-the-blanks-imputing-missing-sentences","title":"Fill in the Blanks: Imputing Missing Sentences for Larger-Context Neural Machine Translation","date":"2019-10-30","arxiv_id":"1910.14075","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-and-efficient-end-to-end-speech","title":"Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer","date":"2019-10-30","arxiv_id":"1910.13923","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-rich-image-region-representation-for","title":"Learning Rich Image Region Representation for Visual Question Answering","date":"2019-10-29","arxiv_id":"1910.13077","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-natural-language-approach-for","title":"Semi-Supervised Natural Language Approach for Fine-Grained Classification of Medical Reports","date":"2019-10-29","arxiv_id":"1910.13573","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-kernel-functions-in-the-softmax","title":"Exploring Kernel Functions in the Softmax Layer for Contextual Word Classification","date":"2019-10-28","arxiv_id":"1910.12554","repositories_listed":0,"syntology":null},{"url":null,"slug":"sketch-fill-a-r-a-persona-grounded-chit-chat","title":"Sketch-Fill-A-R: A Persona-Grounded Chit-Chat Generation Framework","date":"2019-10-28","arxiv_id":"1910.13008","repositories_listed":0,"syntology":null},{"url":null,"slug":"finetext-text-classification-via-attention","title":"FineText: Text Classification via Attention-based Language Model Fine-tuning","date":"2019-10-25","arxiv_id":"1910.11959","repositories_listed":0,"syntology":null},{"url":null,"slug":"l2rs-a-learning-to-rescore-mechanism-for","title":"L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition","date":"2019-10-25","arxiv_id":"1910.11496","repositories_listed":0,"syntology":null},{"url":"/paper/speechbert-cross-modal-pre-trained-language","slug":"speechbert-cross-modal-pre-trained-language","title":"SpeechBERT: An Audio-and-text Jointly Learned Language Model for End-to-end Spoken Question Answering","date":"2019-10-25","arxiv_id":"1910.11559","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-of-efficient-asr-rescoring","title":"An Empirical Study of Efficient ASR Rescoring with Transformers","date":"2019-10-24","arxiv_id":"1910.11450","repositories_listed":0,"syntology":null},{"url":null,"slug":"correction-of-automatic-speech-recognition","title":"Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model","date":"2019-10-23","arxiv_id":"1910.10697","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-dynamic-wfst-decoding-for","title":"Efficient Dynamic WFST Decoding for Personalized Language Models","date":"2019-10-23","arxiv_id":"1910.10670","repositories_listed":0,"syntology":null},{"url":null,"slug":"ner-models-using-pre-training-and-transfer","title":"Healthcare NER Models Using Language Model Pretraining","date":"2019-10-23","arxiv_id":"1910.11241","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-extraction-of-personality-from-text","title":"Automatic Extraction of Personality from Text: Challenges and Opportunities","date":"2019-10-22","arxiv_id":"1910.09916","repositories_listed":0,"syntology":null},{"url":null,"slug":"ipod-corpus-of-190000-industrial-occupations","title":"IPOD: An Industrial and Professional Occupations Dataset and its Applications to Occupational Data Mining and Analysis","date":"2019-10-22","arxiv_id":"1910.10495","repositories_listed":0,"syntology":null},{"url":"/paper/transformer-based-acoustic-modeling-for","slug":"transformer-based-acoustic-modeling-for","title":"Transformer-based Acoustic Modeling for Hybrid Speech Recognition","date":"2019-10-22","arxiv_id":"1910.09799","repositories_listed":0,"syntology":null},{"url":null,"slug":"elsa-a-throughput-optimized-design-of-an-lstm","title":"ELSA: A Throughput-Optimized Design of an LSTM Accelerator for Energy-Constrained Devices","date":"2019-10-19","arxiv_id":"1910.08683","repositories_listed":0,"syntology":null},{"url":null,"slug":"big-mood-relating-transformers-to-explicit","title":"BIG MOOD: Relating Transformers to Explicit Commonsense Knowledge","date":"2019-10-17","arxiv_id":"1910.07713","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-augmented-recurrent-networks-for","title":"Memory-Augmented Recurrent Networks for Dialogue Coherence","date":"2019-10-16","arxiv_id":"1910.10487","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-compact-models-for-low-resource","title":"Training Compact Models for Low Resource Entity Tagging using Pre-trained Language Models","date":"2019-10-14","arxiv_id":"1910.06294","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-exposure-bias-in-language-modeling","title":"Rethinking Exposure Bias In Language Modeling","date":"2019-10-13","arxiv_id":"1910.11235","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-memory-plasticity-for-anomaly","title":"Neural Memory Plasticity for Anomaly Detection","date":"2019-10-12","arxiv_id":"1910.05448","repositories_listed":0,"syntology":null}],"record_sha256":"e5a936be8040caeb77edb066f0d5c0a7e859d75eaabb681f4e263d8e49702e92","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}