{"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/161","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":161,"pages_in_order":177,"rows_per_page":100,"rows":[16001,16100],"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/160","next":"/task/language-modelling/papers/162","papers":[{"url":null,"slug":"compression-of-recurrent-neural-networks-for","title":"Compression of Recurrent Neural Networks for Efficient Language Modeling","date":"2019-02-06","arxiv_id":"1902.02380","repositories_listed":0,"syntology":null},{"url":null,"slug":"doubly-sparse-sparse-mixture-of-sparse","title":"Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference","date":"2019-01-30","arxiv_id":"1901.10668","repositories_listed":0,"syntology":null},{"url":null,"slug":"hardware-guided-symbiotic-training-for","title":"Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM","date":"2019-01-30","arxiv_id":"1901.10997","repositories_listed":0,"syntology":null},{"url":null,"slug":"strong-black-box-adversarial-attacks-on","title":"Strong Black-box Adversarial Attacks on Unsupervised Machine Learning Models","date":"2019-01-28","arxiv_id":"1901.09493","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-smoothing-in-recurrent-neural","title":"Variational Smoothing in Recurrent Neural Network Language Models","date":"2019-01-27","arxiv_id":"1901.09296","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-pre-training-for-hierarchical","title":"Language Model Pre-training for Hierarchical Document Representations","date":"2019-01-26","arxiv_id":"1901.09128","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-regularized-recurrent-neural-networks","title":"State-Regularized Recurrent Neural Networks","date":"2019-01-25","arxiv_id":"1901.08817","repositories_listed":0,"syntology":null},{"url":null,"slug":"error-correcting-neural-sequence-prediction","title":"Error-Correcting Neural Sequence Prediction","date":"2019-01-21","arxiv_id":"1901.07002","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-chinese-word-segmentation-with","title":"Robust Chinese Word Segmentation with Contextualized Word Representations","date":"2019-01-17","arxiv_id":"1901.05816","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-the-mumble-of-wireless-channel","title":"Predicting the Mumble of Wireless Channel with Sequence-to-Sequence Models","date":"2019-01-14","arxiv_id":"1901.04119","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-using-context-dependent-symbols-in","title":"Towards Using Context-Dependent Symbols in CTC Without State-Tying Decision Trees","date":"2019-01-14","arxiv_id":"1901.04379","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-do-language-representations-really","title":"What do Language Representations Really Represent?","date":"2019-01-09","arxiv_id":"1901.02646","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-unsupervised-word-by-word","title":"Improving Unsupervised Word-by-Word Translation with Language Model and Denoising Autoencoder","date":"2019-01-06","arxiv_id":"1901.01590","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-and-rule-based-finnish-nlp-models","title":"Neural and rule-based Finnish NLP models---expectations, experiments and experiences","date":"2019-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-acoustic-to-word-ctc-model-with","title":"Advancing Acoustic-to-Word CTC Model with Attention and Mixed-Units","date":"2018-12-31","arxiv_id":"1812.11928","repositories_listed":0,"syntology":null},{"url":null,"slug":"athena-automated-tuning-of-genomic-error","title":"ATHENA: Automated Tuning of Genomic Error Correction Algorithms using Language Models","date":"2018-12-30","arxiv_id":"1812.11467","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-interpretability-of-deep-neural","title":"Improving the Interpretability of Deep Neural Networks with Knowledge Distillation","date":"2018-12-28","arxiv_id":"1812.10924","repositories_listed":0,"syntology":null},{"url":null,"slug":"looking-for-elmos-friends-sentence-level","title":"Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling","date":"2018-12-28","arxiv_id":"1812.10860","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-lstms-with-adaptive-attention","title":"Hierarchical LSTMs with Adaptive Attention for Visual Captioning","date":"2018-12-26","arxiv_id":"1812.11004","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-dialog-language-model-for-goal","title":"Quantized-Dialog Language Model for Goal-Oriented Conversational Systems","date":"2018-12-26","arxiv_id":"1812.10356","repositories_listed":0,"syntology":null},{"url":null,"slug":"precision-highway-for-ultra-low-precision","title":"Precision Highway for Ultra Low-Precision Quantization","date":"2018-12-24","arxiv_id":"1812.09818","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-speech-recognition-via-segmental","title":"Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching","date":"2018-12-23","arxiv_id":"1812.09323","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-fusion-effects-of-tensor-product","title":"Feature Fusion Effects of Tensor Product Representation on (De)Compositional Network for Caption Generation for Images","date":"2018-12-17","arxiv_id":"1812.06624","repositories_listed":0,"syntology":null},{"url":"/paper/fully-convolutional-speech-recognition","slug":"fully-convolutional-speech-recognition","title":"Fully Convolutional Speech Recognition","date":"2018-12-17","arxiv_id":"1812.06864","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-language-model-adaptation-for-spoken","title":"Scalable language model adaptation for spoken dialogue systems","date":"2018-12-11","arxiv_id":"1812.04647","repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-flexible-adaptive-computational-time","title":"Layer Flexible Adaptive Computational Time","date":"2018-12-06","arxiv_id":"1812.02335","repositories_listed":0,"syntology":null},{"url":"/paper/parameter-re-initialization-through-cyclical","slug":"parameter-re-initialization-through-cyclical","title":"Parameter Re-Initialization through Cyclical Batch Size Schedules","date":"2018-12-04","arxiv_id":"1812.01216","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantification-and-analysis-of-scientific","title":"Quantification and Analysis of Scientific Language Variation Across Research Fields","date":"2018-12-04","arxiv_id":"1812.01250","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-neural-and-n-gram-based-language","title":"Comparing Neural- and N-Gram-Based Language Models for Word Segmentation","date":"2018-12-03","arxiv_id":"1812.00815","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-cache-model-for-image-recognition","title":"A Simple Cache Model for Image Recognition","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"effectiveness-of-character-language-model-for","title":"Effectiveness of Character Language Model for Vietnamese Named Entity Recognition","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-context-into-language-encoding","title":"Incorporating Context into Language Encoding Models for fMRI","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-language-model-fine-tuning-for","title":"Universal Language Model Fine-tuning for Patent Classification","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multimodal-learning-an-effective-method","title":"Deep Multimodal Learning: An Effective Method for Video Classification","date":"2018-11-30","arxiv_id":"1811.12563","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-computational-inefficiency-of-large","title":"On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent","date":"2018-11-30","arxiv_id":"1811.12941","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustics-guided-evaluation-age-a-new-measure","title":"Acoustics-guided evaluation (AGE): a new measure for estimating performance of speech enhancement algorithms for robust ASR","date":"2018-11-28","arxiv_id":"1811.11517","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-2d-lstm-really-dead-for-offline-text","title":"Are 2D-LSTM really dead for offline text recognition?","date":"2018-11-27","arxiv_id":"1811.10899","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-word-discovery-with-segmental","title":"Learning to Discover, Ground and Use Words with Segmental Neural Language Models","date":"2018-11-23","arxiv_id":"1811.09353","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-uncertainties-in-natural-language","title":"Quantifying Uncertainties in Natural Language Processing Tasks","date":"2018-11-18","arxiv_id":"1811.07253","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-cell-lstm-based-neural-language-model","title":"Multi-cell LSTM Based Neural Language Model","date":"2018-11-15","arxiv_id":"1811.06477","repositories_listed":0,"syntology":null},{"url":null,"slug":"extractive-summary-as-discrete-latent","title":"Extractive Summary as Discrete Latent Variables","date":"2018-11-14","arxiv_id":"1811.05542","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-online-attention-based-model-for-speech","title":"An Online Attention-based Model for Speech Recognition","date":"2018-11-13","arxiv_id":"1811.05247","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-rnn-transducer-for-chinese-speech","title":"Exploring RNN-Transducer for Chinese Speech Recognition","date":"2018-11-13","arxiv_id":"1811.05097","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-local-dependence-in-natural-language","title":"Modeling Local Dependence in Natural Language with Multi-channel Recurrent Neural Networks","date":"2018-11-13","arxiv_id":"1811.05121","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-networks-learning-to-decompose-neural","title":"Modular Networks: Learning to Decompose Neural Computation","date":"2018-11-13","arxiv_id":"1811.05249","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-of-language-models-with","title":"Fine-tuning of Language Models with Discriminator","date":"2018-11-12","arxiv_id":"1811.04623","repositories_listed":0,"syntology":null},{"url":null,"slug":"forecasting-peoples-needs-in-hurricane-events","title":"Forecasting People's Needs in Hurricane Events from Social Network","date":"2018-11-12","arxiv_id":"1811.04577","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-training-of-rnnlms-with-the","title":"Discriminative training of RNNLMs with the average word error criterion","date":"2018-11-06","arxiv_id":"1811.02528","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-integration-based-on-memory","title":"Language model integration based on memory control for sequence to sequence speech recognition","date":"2018-11-06","arxiv_id":"1811.02162","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-of-language-independent-end","title":"Transfer learning of language-independent end-to-end ASR with language model fusion","date":"2018-11-06","arxiv_id":"1811.02134","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-marchex-2018-english-conversational","title":"The Marchex 2018 English Conversational Telephone Speech Recognition System","date":"2018-11-05","arxiv_id":"1811.02058","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unsupervised-speech-to-text","title":"Towards Unsupervised Speech-to-Text Translation","date":"2018-11-04","arxiv_id":"1811.01307","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-training-of-end-to-end-speech","title":"Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model","date":"2018-11-02","arxiv_id":"1811.00787","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysing-dropout-and-compounding-errors-in","title":"Analysing Dropout and Compounding Errors in Neural Language Models","date":"2018-11-02","arxiv_id":"1811.00998","repositories_listed":0,"syntology":null},{"url":null,"slug":"cycle-consistency-training-for-end-to-end","title":"Cycle-consistency training for end-to-end speech recognition","date":"2018-11-02","arxiv_id":"1811.01690","repositories_listed":0,"syntology":null},{"url":null,"slug":"progress-and-tradeoffs-in-neural-language","title":"Progress and Tradeoffs in Neural Language Models","date":"2018-11-02","arxiv_id":"1811.00942","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-neural-speech-recognition-systems","title":"Training Neural Speech Recognition Systems with Synthetic Speech Augmentation","date":"2018-11-02","arxiv_id":"1811.00707","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-birds-eye-view-on-coherence-and-a-worms-eye","title":"Towards Coherent and Cohesive Long-form Text Generation","date":"2018-11-01","arxiv_id":"1811.00511","repositories_listed":0,"syntology":null},{"url":null,"slug":"closing-brackets-with-recurrent-neural","title":"Closing Brackets with Recurrent Neural Networks","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutions-are-all-you-need-for-classifying","title":"Convolutions Are All You Need (For Classifying Character Sequences)","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"does-syntactic-knowledge-in-multilingual","title":"Does Syntactic Knowledge in Multilingual Language Models Transfer Across Languages?","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"er-well-it-matters-right-on-the-role-of-data","title":"Er ... well, it matters, right? On the role of data representations in spoken language dependency parsing","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"importance-of-self-attention-for-sentiment","title":"Importance of Self-Attention for Sentiment Analysis","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"indicatements-that-character-language-models-1","title":"`Indicatements' that character language models learn English morpho-syntactic units and regularities","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-word-level-hidden-state","title":"Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-modeling-teaches-you-more-than","title":"Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-learn-pos-first","title":"Language Models Learn POS First","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-define-terms-in-the-software","title":"Learning to Define Terms in the Software Domain","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-of-word-meaning-in-the","title":"Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-learning-dynamics-of-language","title":"Understanding Learning Dynamics Of Language Models with SVCCA","date":"2018-11-01","arxiv_id":"1811.00225","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-do-rnn-language-models-learn-about","title":"What do RNN Language Models Learn about Filler--Gap Dependencies?","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-cross-lingual-sentence","title":"Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model","date":"2018-10-30","arxiv_id":"1810.12836","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-attention-unit","title":"Recurrent Attention Unit","date":"2018-10-30","arxiv_id":"1810.12754","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-end-to-end-automatic-code-switching","title":"Towards End-to-end Automatic Code-Switching Speech Recognition","date":"2018-10-30","arxiv_id":"1810.12620","repositories_listed":0,"syntology":null},{"url":null,"slug":"cascaded-cnn-resbilstm-ctc-an-end-to-end","title":"Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition","date":"2018-10-29","arxiv_id":"1810.12001","repositories_listed":0,"syntology":null},{"url":null,"slug":"counting-in-language-with-rnns","title":"Counting in Language with RNNs","date":"2018-10-29","arxiv_id":"1810.12411","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-entropy-explain-successor-surprisal","title":"Can Entropy Explain Successor Surprisal Effects in Reading?","date":"2018-10-26","arxiv_id":"1810.11481","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-to-code-switch-data-augmentation-using","title":"Learn to Code-Switch: Data Augmentation using Copy Mechanism on Language Modeling","date":"2018-10-24","arxiv_id":"1810.10254","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-generative-acoustic-model-for","title":"A Deep Generative Acoustic Model for Compositional Automatic Speech Recognition","date":"2018-10-23","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-modeling-at-scale","title":"Language Modeling at Scale","date":"2018-10-23","arxiv_id":"1810.10045","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-transition-based-syntactic","title":"Neural Transition-based Syntactic Linearization","date":"2018-10-23","arxiv_id":"1810.09609","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-hmms-and-rnns-through-architectural","title":"Bridging HMMs and RNNs through Architectural Transformations","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"training-neural-speech-recognition-systems-1","title":"Training Neural Speech Recognition Systems with Synthetic Speech Augmentation","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-neural-based-input-method","title":"Real-time Neural-based Input Method","date":"2018-10-19","arxiv_id":"1810.09309","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-use-of-attention-within-an","title":"Exploring the Use of Attention within an Neural Machine Translation Decoder States to Translate Idioms","date":"2018-10-10","arxiv_id":"1810.06695","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-recurrent-neural-architectures","title":"Understanding Recurrent Neural Architectures by Analyzing and Synthesizing Long Distance Dependencies in Benchmark Sequential Datasets","date":"2018-10-06","arxiv_id":"1810.02966","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-sequence-to-sequence-speech","title":"Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling","date":"2018-10-04","arxiv_id":"1810.03459","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-self-attentive-model-with-gate-mechanism","title":"A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"alibaba-submission-for-wmt18-quality","title":"Alibaba Submission for WMT18 Quality Estimation Task","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-of-machine-translation-for","title":"An Empirical Study of Machine Translation for the Shared Task of WMT18","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-unsupervised-system-for-parallel-corpus","title":"An Unsupervised System for Parallel Corpus Filtering","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bidirectional-generative-adversarial-networks","title":"Bidirectional Generative Adversarial Networks for Neural Machine Translation","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coreference-and-coherence-in-neural-machine","title":"Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decipherment-of-substitution-ciphers-with","title":"Decipherment of Substitution Ciphers with Neural Language Models","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"disney-at-iest-2018-predicting-emotions-using","title":"Disney at IEST 2018: Predicting Emotions using an Ensemble","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-fixed-size-ordinally-forgetting-encoding","title":"Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eeae3e34-ea12c-eaee3e-a1eae-aeaee-on-the-use","title":"會議語音辨識使用語者資訊之語言模型調適技術 (On the Use of Speaker-Aware Language Model Adaptation Techniques for Meeting Speech Recognition ) [In Chinese]","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"elmolex-connecting-elmo-and-lexicon-features","title":"ELMoLex: Connecting ELMo and Lexicon Features for Dependency Parsing","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-marginal-probabilities-of-n-grams","title":"Estimating Marginal Probabilities of n-grams for Recurrent Neural Language Models","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-represent-a-word-and-predict-it-too","title":"How to represent a word and predict it, too: Improving tied architectures for language modelling","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"1050eb52d5937eabad4703387d1f4ace0dc8d3399ad40bc899a7c2045bff8fff","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}