{"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-modeling/papers/130","list_of":"/task/language-modeling","task":"Language Modeling","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":130,"pages_in_order":142,"rows_per_page":100,"rows":[12901,13000],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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-modeling","prev":"/task/language-modeling/papers/129","next":"/task/language-modeling/papers/131","papers":[{"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":"vais-asr-building-a-conversational-speech","title":"VAIS ASR: Building a conversational speech recognition system using language model combination","date":"2019-10-12","arxiv_id":"1910.05603","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-people-prefer-natural-code","title":"Do People Prefer \"Natural\" code?","date":"2019-10-08","arxiv_id":"1910.03704","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-zero-inflated-quality-estimation-model","title":"Neural Zero-Inflated Quality Estimation Model For Automatic Speech Recognition System","date":"2019-10-03","arxiv_id":"1910.01289","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilled-embedding-non-linear-embedding","title":"Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition","date":"2019-10-02","arxiv_id":"1910.06720","repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-for-question-generation","title":"BERT for Question Generation","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-argumentation-synthesis-as-a","title":"Computational Argumentation Synthesis as a Language Modeling Task","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-contents-in-data-to-document","title":"Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-in-generation-a-closer-look-at","title":"Generalization in Generation: A closer look at Exposure Bias","date":"2019-10-01","arxiv_id":"1910.00292","repositories_listed":0,"syntology":null},{"url":null,"slug":"generation-of-hip-hop-lyrics-with","title":"Generation of Hip-Hop Lyrics with Hierarchical Modeling and Conditional Templates","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-variable-generative-models-for-data","title":"Latent-Variable Generative Models for Data-Efficient Text Classification","date":"2019-10-01","arxiv_id":"1910.00382","repositories_listed":0,"syntology":null},{"url":"/paper/neural-generation-for-czech-data-and-1","slug":"neural-generation-for-czech-data-and-1","title":"Neural Generation for Czech: Data and Baselines","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"putting-machine-translation-in-context-with-1","title":"Better Document-Level Machine Translation with Bayes' Rule","date":"2019-10-01","arxiv_id":"1910.00553","repositories_listed":0,"syntology":null},{"url":null,"slug":"tmlab-generative-enhanced-model-gem-for","title":"TMLab: Generative Enhanced Model (GEM) for adversarial attacks","date":"2019-10-01","arxiv_id":"1910.00337","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-goes-into-a-word-generating-image","title":"What goes into a word: generating image descriptions with top-down spatial knowledge","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-neural-topic-learning-in","title":"Lifelong Neural Topic Learning in Contextualized Autoregressive Topic Models of Language via Informative Transfers","date":"2019-09-29","arxiv_id":"1909.13315","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-detection-of-distributional-discrepancy-1","title":"The Detection of Distributional Discrepancy for Text Generation","date":"2019-09-28","arxiv_id":"1910.04859","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-code-switching-asr-for-low","title":"End-to-End Code-Switching ASR for Low-Resourced Language Pairs","date":"2019-09-27","arxiv_id":"1909.12681","repositories_listed":0,"syntology":null},{"url":null,"slug":"biomedical-relation-extraction-with-pre","title":"Biomedical relation extraction with pre-trained language representations and minimal task-specific architecture","date":"2019-09-26","arxiv_id":"1909.12411","repositories_listed":0,"syntology":null},{"url":null,"slug":"darts-dialectal-arabic-transcription-system","title":"DARTS: Dialectal Arabic Transcription System","date":"2019-09-26","arxiv_id":"1909.12163","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-pre-trained-multilingual-models","title":"Improving Pre-Trained Multilingual Models with Vocabulary Expansion","date":"2019-09-26","arxiv_id":"1909.12440","repositories_listed":0,"syntology":null},{"url":null,"slug":"anchor-transform-learning-sparse","title":"Anchor & Transform: Learning Sparse Representations of Discrete Objects","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"asgen-answer-containing-sentence-generation","title":"ASGen: Answer-containing Sentence Generation to Pre-Train Question Generator for Scale-up Data in Question Answering","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-attention-with-explicit-phrasal","title":"Enhancing Attention with Explicit Phrasal Alignments","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"forecasting-deep-learning-dynamics-with","title":"Forecasting Deep Learning Dynamics with Applications to Hyperparameter Tuning","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"group-transformer-towards-a-lightweight","title":"Group-Transformer: Towards A Lightweight Character-level Language Model","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-network-structure-for-modeling","title":"Interpretable Network Structure for Modeling Contextual Dependency","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-flexible-adaptive-computation-time-for","title":"Layer Flexible Adaptive Computation Time for Recurrent Neural Networks","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lossless-data-compression-with-transformer","title":"Lossless Data Compression with Transformer","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"putting-machine-translation-in-context-with","title":"Putting Machine Translation in Context with the Noisy Channel Model","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-hierarchical-topic-guided-neural","title":"Recurrent Hierarchical Topic-Guided Neural Language Models","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-neural-learning-for-verifiable","title":"Scalable Neural Learning for Verifiable Consistency with Temporal Specifications","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-speech-recognition-via-local","title":"Self-Supervised Speech Recognition via Local Prior Matching","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"softadam-unifying-sgd-and-adam-for-better","title":"SoftAdam: Unifying SGD and Adam for better stochastic gradient descent","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-transformer-concentrated-attention","title":"Sparse Transformer: Concentrated Attention Through Explicit Selection","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"structural-language-models-for-any-code-1","title":"Structural Language Models for Any-Code Generation","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uniter-learning-universal-image-text","title":"UNITER: Learning UNiversal Image-TExt Representations","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"xd-cross-lingual-knowledge-distillation-for","title":"XD: Cross-lingual Knowledge Distillation for Polyglot Sentence Embeddings","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"code-switching-language-modeling-with","title":"Code-switching Language Modeling With Bilingual Word Embeddings: A Case Study for Egyptian Arabic-English","date":"2019-09-24","arxiv_id":"1909.10892","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-semantics-from-speech-through","title":"Understanding Semantics from Speech Through Pre-training","date":"2019-09-24","arxiv_id":"1909.10924","repositories_listed":0,"syntology":null},{"url":null,"slug":"190909962","title":"Adapting Language Models for Non-Parallel Author-Stylized Rewriting","date":"2019-09-22","arxiv_id":"1909.09962","repositories_listed":0,"syntology":null},{"url":null,"slug":"190910056","title":"Inducing Constituency Trees through Neural Machine Translation","date":"2019-09-22","arxiv_id":"1909.10056","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-hybrid-and-end-to-end-models","title":"A Comparison of Hybrid and End-to-End Models for Syllable Recognition","date":"2019-09-19","arxiv_id":"1909.12232","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-random-gossip-bmuf-process-for-neural","title":"A Random Gossip BMUF Process for Neural Language Modeling","date":"2019-09-19","arxiv_id":"1909.09010","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-ways-to-incorporate-additional","title":"How Additional Knowledge can Improve Natural Language Commonsense Question Answering?","date":"2019-09-19","arxiv_id":"1909.08855","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-training-for-end-to-end-speech","title":"Self-Training for End-to-End Speech Recognition","date":"2019-09-19","arxiv_id":"1909.09116","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-switched-language-models-using-neural","title":"Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences","date":"2019-09-18","arxiv_id":"1909.08582","repositories_listed":0,"syntology":null},{"url":null,"slug":"character-centric-storytelling","title":"Character-Centric Storytelling","date":"2019-09-17","arxiv_id":"1909.07863","repositories_listed":0,"syntology":null},{"url":null,"slug":"relaxed-softmax-for-learning-from-positive","title":"Relaxed Softmax for learning from Positive and Unlabeled data","date":"2019-09-17","arxiv_id":"1909.08079","repositories_listed":0,"syntology":null},{"url":null,"slug":"bottlesum-unsupervised-and-self-supervised","title":"BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle","date":"2019-09-16","arxiv_id":"1909.07405","repositories_listed":0,"syntology":null},{"url":null,"slug":"constructing-dynamic-knowledge-graph-for","title":"Bridging Visual Perception with Contextual Semantics for Understanding Robot Manipulation Tasks","date":"2019-09-16","arxiv_id":"1909.07459","repositories_listed":0,"syntology":null},{"url":null,"slug":"short-text-classification-using-unsupervised","title":"Short-Text Classification Using Unsupervised Keyword Expansion","date":"2019-09-16","arxiv_id":"1909.07512","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-in-geology-and","title":"Representation Learning in Geology and GilBERT","date":"2019-09-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-structure-extraction-for-spreadsheet","title":"Semantic Structure Extraction for Spreadsheet Tables with a Multi-task Learning Architecture","date":"2019-09-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"differentially-private-meta-learning","title":"Differentially Private Meta-Learning","date":"2019-09-12","arxiv_id":"1909.05830","repositories_listed":0,"syntology":null},{"url":null,"slug":"speculative-beam-search-for-simultaneous","title":"Speculative Beam Search for Simultaneous Translation","date":"2019-09-12","arxiv_id":"1909.05421","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-fusion-attentional-language-model-for","title":"Dynamic Fusion: Attentional Language Model for Neural Machine Translation","date":"2019-09-11","arxiv_id":"1909.04879","repositories_listed":0,"syntology":null},{"url":null,"slug":"countering-language-drift-via-visual","title":"Countering Language Drift via Visual Grounding","date":"2019-09-10","arxiv_id":"1909.04499","repositories_listed":0,"syntology":null},{"url":null,"slug":"reverse-transfer-learning-can-word-embeddings","title":"Reverse Transfer Learning: Can Word Embeddings Trained for Different NLP Tasks Improve Neural Language Models?","date":"2019-09-09","arxiv_id":"1909.04130","repositories_listed":0,"syntology":null},{"url":"/paper/auto-gnn-neural-architecture-search-of-graph","slug":"auto-gnn-neural-architecture-search-of-graph","title":"Auto-GNN: Neural Architecture Search of Graph Neural Networks","date":"2019-09-07","arxiv_id":"1909.03184","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-examples-with-difficult-common","title":"Robustness to Modification with Shared Words in Paraphrase Identification","date":"2019-09-05","arxiv_id":"1909.02560","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-argument-quality-assessment-new","title":"Automatic Argument Quality Assessment -- New Datasets and Methods","date":"2019-09-03","arxiv_id":"1909.01007","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-bottom-up-evolution-of-representations-in","title":"The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives","date":"2019-09-03","arxiv_id":"1909.01380","repositories_listed":0,"syntology":null},{"url":null,"slug":"unicoder-a-universal-language-encoder-by-pre","title":"Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks","date":"2019-09-03","arxiv_id":"1909.00964","repositories_listed":0,"syntology":null},{"url":null,"slug":"enriching-medcial-terminology-knowledge-bases","title":"Enriching Medcial Terminology Knowledge Bases via Pre-trained Language Model and Graph Convolutional Network","date":"2019-09-02","arxiv_id":"1909.00615","repositories_listed":0,"syntology":null},{"url":null,"slug":"phrase-level-class-based-language-model-for","title":"Phrase-Level Class based Language Model for Mandarin Smart Speaker Query Recognition","date":"2019-09-02","arxiv_id":"1909.00556","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-syntactically-expressive-morphological","title":"A Syntactically Expressive Morphological Analyzer for Turkish","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-unsupervised-query-rewriting-approach","title":"An Unsupervised Query Rewriting Approach Using N-gram Co-occurrence Statistics to Find Similar Phrases in Large Text Corpora","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"e8a22473087b7e927d848e9010d7d8f7f1dad8ca790c81387f11bd4475ae07fc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}