{"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/68","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":68,"pages_in_order":177,"rows_per_page":100,"rows":[6701,6800],"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/67","next":"/task/language-modelling/papers/69","papers":[{"url":"/paper/detect-camouflaged-spam-content-via","slug":"detect-camouflaged-spam-content-via","title":"Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation","date":"2019-08-30","arxiv_id":"1908.11561","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-deep-latent-variable-models-for-text","slug":"implicit-deep-latent-variable-models-for-text","title":"Implicit Deep Latent Variable Models for Text Generation","date":"2019-08-30","arxiv_id":"1908.11527","repositories_listed":1,"syntology":null},{"url":"/paper/linguistic-versus-latent-relations-for","slug":"linguistic-versus-latent-relations-for","title":"Linguistic Versus Latent Relations for Modeling Coherent Flow in Paragraphs","date":"2019-08-30","arxiv_id":"1908.11790","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-domain-adaptation-for-neural","slug":"unsupervised-domain-adaptation-for-neural","title":"Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings","date":"2019-08-27","arxiv_id":"1908.10430","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unsupervised-domain-adaptation-for-neural#ran","syntology_url":"https://syntology.ai/paper/1908.10430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.10430"}},"official":{"repos":["zdou0830/DAFE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/uniblock-scoring-and-filtering-corpus-with","slug":"uniblock-scoring-and-filtering-corpus-with","title":"uniblock: Scoring and Filtering Corpus with Unicode Block Information","date":"2019-08-26","arxiv_id":"1908.09716","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uniblock-scoring-and-filtering-corpus-with#ran","syntology_url":"https://syntology.ai/paper/1908.09716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09716"}},"official":{"repos":["ringoreality/uniblock"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-learning-based-chatbot-models","slug":"deep-learning-based-chatbot-models","title":"Deep Learning Based Chatbot Models","date":"2019-08-23","arxiv_id":"1908.08835","repositories_listed":1,"syntology":null},{"url":"/paper/190807721","slug":"190807721","title":"Fine-tuning BERT for Joint Entity and Relation Extraction in Chinese Medical Text","date":"2019-08-21","arxiv_id":"1908.07721","repositories_listed":1,"syntology":null},{"url":"/paper/190807724","slug":"190807724","title":"Restricted Recurrent Neural Networks","date":"2019-08-21","arxiv_id":"1908.07724","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/190807724#ran","syntology_url":"https://syntology.ai/paper/1908.07724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07724"}},"official":{"repos":["diaoenmao/Restricted-Recurrent-Neural-Networks"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/190808025","slug":"190808025","title":"WikiCREM: A Large Unsupervised Corpus for Coreference Resolution","date":"2019-08-21","arxiv_id":"1908.08025","repositories_listed":1,"syntology":null},{"url":"/paper/universal-adversarial-triggers-for-nlp","slug":"universal-adversarial-triggers-for-nlp","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","date":"2019-08-20","arxiv_id":"1908.07125","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/universal-adversarial-triggers-for-nlp#ran","syntology_url":"https://syntology.ai/paper/1908.07125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07125"}},"official":{"repos":["Eric-Wallace/universal-triggers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/encoder-agnostic-adaptation-for-conditional","slug":"encoder-agnostic-adaptation-for-conditional","title":"Encoder-Agnostic Adaptation for Conditional Language Generation","date":"2019-08-19","arxiv_id":"1908.06938","repositories_listed":1,"syntology":null},{"url":"/paper/emotionx-idea-emotion-bert-an-affectional","slug":"emotionx-idea-emotion-bert-an-affectional","title":"EmotionX-IDEA: Emotion BERT -- an Affectional Model for Conversation","date":"2019-08-17","arxiv_id":"1908.06264","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-evaluation-of-machine-translation","slug":"on-the-evaluation-of-machine-translation","title":"On The Evaluation of Machine Translation Systems Trained With Back-Translation","date":"2019-08-14","arxiv_id":"1908.05204","repositories_listed":1,"syntology":null},{"url":"/paper/sg-net-syntax-guided-machine-reading","slug":"sg-net-syntax-guided-machine-reading","title":"SG-Net: Syntax-Guided Machine Reading Comprehension","date":"2019-08-14","arxiv_id":"1908.05147","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptive-training-bert-for-response","slug":"domain-adaptive-training-bert-for-response","title":"An Effective Domain Adaptive Post-Training Method for BERT in Response Selection","date":"2019-08-13","arxiv_id":"1908.04812","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-3d-human-dynamics-from-video","slug":"predicting-3d-human-dynamics-from-video","title":"Predicting 3D Human Dynamics from Video","date":"2019-08-13","arxiv_id":"1908.04781","repositories_listed":1,"syntology":{"n":17,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/predicting-3d-human-dynamics-from-video#ran","syntology_url":"https://syntology.ai/paper/1908.04781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.04781"}},"official":{"repos":["jasonyzhang/phd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/clustering-of-deep-contextualized","slug":"clustering-of-deep-contextualized","title":"Clustering of Deep Contextualized Representations for Summarization of Biomedical Texts","date":"2019-08-06","arxiv_id":"1908.02286","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-on-pre-trained-embeddings","slug":"an-empirical-study-on-pre-trained-embeddings","title":"An Empirical Study on Pre-trained Embeddings and Language Models for Bot Detection","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-lstm-adaptation-study-of-ungrammaticality","slug":"an-lstm-adaptation-study-of-ungrammaticality","title":"An LSTM Adaptation Study of (Un)grammaticality","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/finding-hierarchical-structure-in-neural","slug":"finding-hierarchical-structure-in-neural","title":"Finding Hierarchical Structure in Neural Stacks Using Unsupervised Parsing","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hulmona-the-universal-language-model-in","slug":"hulmona-the-universal-language-model-in","title":"hULMonA: The Universal Language Model in Arabic","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/simple-unsupervised-summarization-by-1","slug":"simple-unsupervised-summarization-by-1","title":"Simple Unsupervised Summarization by Contextual Matching","date":"2019-07-31","arxiv_id":"1907.13337","repositories_listed":1,"syntology":null},{"url":"/paper/representation-degeneration-problem-in-1","slug":"representation-degeneration-problem-in-1","title":"Representation Degeneration Problem in Training Natural Language Generation Models","date":"2019-07-28","arxiv_id":"1907.12009","repositories_listed":1,"syntology":null},{"url":"/paper/bilingual-lexicon-induction-through","slug":"bilingual-lexicon-induction-through","title":"Bilingual Lexicon Induction through Unsupervised Machine Translation","date":"2019-07-24","arxiv_id":"1907.10761","repositories_listed":1,"syntology":null},{"url":"/paper/language-modelling-for-sound-event-detection","slug":"language-modelling-for-sound-event-detection","title":"Language Modelling for Sound Event Detection with Teacher Forcing and Scheduled Sampling","date":"2019-07-19","arxiv_id":"1907.08506","repositories_listed":1,"syntology":null},{"url":"/paper/neural-shuffle-exchange-networks-sequence","slug":"neural-shuffle-exchange-networks-sequence","title":"Neural Shuffle-Exchange Networks -- Sequence Processing in O(n log n) Time","date":"2019-07-18","arxiv_id":"1907.07897","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-shuffle-exchange-networks-sequence#ran","syntology_url":"https://syntology.ai/paper/1907.07897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.07897"}},"official":{"repos":["LUMII-Syslab/shuffle-exchange"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-language-model-based-training-data","slug":"neural-language-model-based-training-data","title":"Neural Language Model Based Training Data Augmentation for Weakly Supervised Early Rumor Detection","date":"2019-07-16","arxiv_id":"1907.07033","repositories_listed":1,"syntology":null},{"url":"/paper/agglomerative-attention","slug":"agglomerative-attention","title":"Agglomerative Attention","date":"2019-07-15","arxiv_id":"1907.06607","repositories_listed":1,"syntology":null},{"url":"/paper/hello-its-gpt-2-how-can-i-help-you-towards","slug":"hello-its-gpt-2-how-can-i-help-you-towards","title":"Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems","date":"2019-07-12","arxiv_id":"1907.05774","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-phonetic-and-graphemic","slug":"analyzing-phonetic-and-graphemic","title":"Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition","date":"2019-07-09","arxiv_id":"1907.04224","repositories_listed":1,"syntology":null},{"url":"/paper/applying-a-pre-trained-language-model-to","slug":"applying-a-pre-trained-language-model-to","title":"Applying a Pre-trained Language Model to Spanish Twitter Humor Prediction","date":"2019-07-06","arxiv_id":"1907.03187","repositories_listed":1,"syntology":null},{"url":"/paper/baracks-wife-hillary-using-knowledge-graphs-1","slug":"baracks-wife-hillary-using-knowledge-graphs-1","title":"Barack's Wife Hillary: Using Knowledge Graphs for Fact-Aware Language Modeling","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-domain-ner-using-cross-domain-language","slug":"cross-domain-ner-using-cross-domain-language","title":"Cross-Domain NER using Cross-Domain Language Modeling","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/task-refinement-learning-for-improved","slug":"task-refinement-learning-for-improved","title":"Task Refinement Learning for Improved Accuracy and Stability of Unsupervised Domain Adaptation","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/supervised-contextual-embeddings-for-transfer","slug":"supervised-contextual-embeddings-for-transfer","title":"Supervised Contextual Embeddings for Transfer Learning in Natural Language Processing Tasks","date":"2019-06-28","arxiv_id":"1906.12039","repositories_listed":1,"syntology":null},{"url":"/paper/a-tensorized-transformer-for-language","slug":"a-tensorized-transformer-for-language","title":"A Tensorized Transformer for Language Modeling","date":"2019-06-24","arxiv_id":"1906.09777","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/a-tensorized-transformer-for-language#ran","syntology_url":"https://syntology.ai/paper/1906.09777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.09777"}},"official":{"repos":["szhangtju/The-compression-of-Transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/language-modelling-makes-sense-propagating","slug":"language-modelling-makes-sense-propagating","title":"Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation","date":"2019-06-24","arxiv_id":"1906.10007","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-pre-trained-transformer-language-1","slug":"fine-tuning-pre-trained-transformer-language-1","title":"Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction","date":"2019-06-19","arxiv_id":"1906.08646","repositories_listed":1,"syntology":null},{"url":"/paper/baracks-wife-hillary-using-knowledge-graphs","slug":"baracks-wife-hillary-using-knowledge-graphs","title":"Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling","date":"2019-06-17","arxiv_id":"1906.07241","repositories_listed":1,"syntology":null},{"url":"/paper/fixing-gaussian-mixture-vaes-for","slug":"fixing-gaussian-mixture-vaes-for","title":"Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation","date":"2019-06-16","arxiv_id":"1906.06719","repositories_listed":1,"syntology":null},{"url":"/paper/continual-and-multi-task-architecture-search","slug":"continual-and-multi-task-architecture-search","title":"Continual and Multi-Task Architecture Search","date":"2019-06-12","arxiv_id":"1906.05226","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continual-and-multi-task-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1906.05226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05226"}},"official":{"repos":["ramakanth-pasunuru/CAS-MAS"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/putting-words-in-context-lstm-language-models","slug":"putting-words-in-context-lstm-language-models","title":"Putting words in context: LSTM language models and lexical ambiguity","date":"2019-06-12","arxiv_id":"1906.05149","repositories_listed":1,"syntology":null},{"url":"/paper/what-does-bert-look-at-an-analysis-of-berts","slug":"what-does-bert-look-at-an-analysis-of-berts","title":"What Does BERT Look At? An Analysis of BERT's Attention","date":"2019-06-11","arxiv_id":"1906.04341","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/what-does-bert-look-at-an-analysis-of-berts#ran","syntology_url":"https://syntology.ai/paper/1906.04341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04341"}},"official":{"repos":["clarkkev/attention-analysis"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/improving-neural-language-modeling-via","slug":"improving-neural-language-modeling-via","title":"Improving Neural Language Modeling via Adversarial Training","date":"2019-06-10","arxiv_id":"1906.03805","repositories_listed":1,"syntology":null},{"url":"/paper/selfie-self-supervised-pretraining-for-image","slug":"selfie-self-supervised-pretraining-for-image","title":"Selfie: Self-supervised Pretraining for Image Embedding","date":"2019-06-07","arxiv_id":"1906.02940","repositories_listed":1,"syntology":null},{"url":"/paper/an-imitation-learning-approach-to","slug":"an-imitation-learning-approach-to","title":"An Imitation Learning Approach to Unsupervised Parsing","date":"2019-06-05","arxiv_id":"1906.02276","repositories_listed":1,"syntology":null},{"url":"/paper/finding-syntactic-representations-in-neural","slug":"finding-syntactic-representations-in-neural","title":"Finding Syntactic Representations in Neural Stacks","date":"2019-06-04","arxiv_id":"1906.01594","repositories_listed":1,"syntology":null},{"url":"/paper/improving-neural-language-models-by","slug":"improving-neural-language-models-by","title":"Improving Neural Language Models by Segmenting, Attending, and Predicting the Future","date":"2019-06-04","arxiv_id":"1906.01702","repositories_listed":1,"syntology":null},{"url":"/paper/training-neural-response-selection-for-task","slug":"training-neural-response-selection-for-task","title":"Training Neural Response Selection for Task-Oriented Dialogue Systems","date":"2019-06-04","arxiv_id":"1906.01543","repositories_listed":1,"syntology":null},{"url":"/paper/190600584","slug":"190600584","title":"A Semi-Supervised Approach for Low-Resourced Text Generation","date":"2019-06-03","arxiv_id":"1906.00584","repositories_listed":1,"syntology":null},{"url":"/paper/190600346","slug":"190600346","title":"Pre-training of Graph Augmented Transformers for Medication Recommendation","date":"2019-06-02","arxiv_id":"1906.00346","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/190600346#ran","syntology_url":"https://syntology.ai/paper/1906.00346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00346"}},"official":{"repos":["jshang123/G-Bert"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/enabling-real-time-neural-ime-with","slug":"enabling-real-time-neural-ime-with","title":"Enabling Real-time Neural IME with Incremental Vocabulary Selection","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-complex-neural-network","slug":"rethinking-complex-neural-network","title":"Rethinking Complex Neural Network Architectures for Document Classification","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/seq3-differentiable-sequence-to-sequence-to-1","slug":"seq3-differentiable-sequence-to-sequence-to-1","title":"SEQ\\^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/what-a-neural-language-model-tells-us-about","slug":"what-a-neural-language-model-tells-us-about","title":"What a neural language model tells us about spatial relations","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/190600041","slug":"190600041","title":"Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval","date":"2019-05-31","arxiv_id":"1906.00041","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-of-gradient-clipping-and-adaptive","slug":"analysis-of-gradient-clipping-and-adaptive","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","date":"2019-05-28","arxiv_id":"1905.11881","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/analysis-of-gradient-clipping-and-adaptive#ran","syntology_url":"https://syntology.ai/paper/1905.11881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11881"}},"official":{"repos":["JingzhaoZhang/why-clipping-accelerates"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/better-long-range-dependency-by-bootstrapping","slug":"better-long-range-dependency-by-bootstrapping","title":"Better Long-Range Dependency By Bootstrapping A Mutual Information Regularizer","date":"2019-05-28","arxiv_id":"1905.11978","repositories_listed":1,"syntology":null},{"url":"/paper/is-a-single-vector-enough-exploring-node","slug":"is-a-single-vector-enough-exploring-node","title":"Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding","date":"2019-05-25","arxiv_id":"1905.10668","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/is-a-single-vector-enough-exploring-node#ran","syntology_url":"https://syntology.ai/paper/1905.10668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.10668"}},"official":null}},{"url":"/paper/soft-contextual-data-augmentation-for-neural","slug":"soft-contextual-data-augmentation-for-neural","title":"Soft Contextual Data Augmentation for Neural Machine Translation","date":"2019-05-25","arxiv_id":"1905.10523","repositories_listed":1,"syntology":null},{"url":"/paper/deeper-text-understanding-for-ir-with","slug":"deeper-text-understanding-for-ir-with","title":"Deeper Text Understanding for IR with Contextual Neural Language Modeling","date":"2019-05-22","arxiv_id":"1905.09217","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/deeper-text-understanding-for-ir-with#ran","syntology_url":"https://syntology.ai/paper/1905.09217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09217"}},"official":{"repos":["AdeDZY/SIGIR19-BERT-IR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-domain-word-embedding-via-latent","slug":"enhancing-domain-word-embedding-via-latent","title":"Enhancing Domain Word Embedding via Latent Semantic Imputation","date":"2019-05-21","arxiv_id":"1905.08900","repositories_listed":1,"syntology":null},{"url":"/paper/adaptively-truncating-backpropagation-through","slug":"adaptively-truncating-backpropagation-through","title":"Adaptively Truncating Backpropagation Through Time to Control Gradient Bias","date":"2019-05-17","arxiv_id":"1905.07473","repositories_listed":1,"syntology":{"n":21,"n_ran":18,"n_constructed":0,"n_ran_checked":18,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":18,"n_pointer_only":0,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/adaptively-truncating-backpropagation-through#ran","syntology_url":"https://syntology.ai/paper/1905.07473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07473"}},"official":{"repos":["aicherc/adaptive_tbptt"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/story-ending-prediction-by-transferable-bert","slug":"story-ending-prediction-by-transferable-bert","title":"Story Ending Prediction by Transferable BERT","date":"2019-05-17","arxiv_id":"1905.07504","repositories_listed":1,"syntology":null},{"url":"/paper/imho-fine-tuning-improves-claim-detection","slug":"imho-fine-tuning-improves-claim-detection","title":"IMHO Fine-Tuning Improves Claim Detection","date":"2019-05-16","arxiv_id":"1905.07000","repositories_listed":1,"syntology":null},{"url":"/paper/online-normalization-for-training-neural","slug":"online-normalization-for-training-neural","title":"Online Normalization for Training Neural Networks","date":"2019-05-15","arxiv_id":"1905.05894","repositories_listed":1,"syntology":{"n":16,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/online-normalization-for-training-neural#ran","syntology_url":"https://syntology.ai/paper/1905.05894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05894"}},"official":{"repos":["cerebras/online-normalization"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-residual-output-layers-for-neural","slug":"deep-residual-output-layers-for-neural","title":"Deep Residual Output Layers for Neural Language Generation","date":"2019-05-14","arxiv_id":"1905.05513","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-use-of-arxiv-as-a-dataset","slug":"on-the-use-of-arxiv-as-a-dataset","title":"On the Use of ArXiv as a Dataset","date":"2019-04-30","arxiv_id":"1905.00075","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/on-the-use-of-arxiv-as-a-dataset#ran","syntology_url":"https://syntology.ai/paper/1905.00075","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.00075"}},"official":{"repos":["mattbierbaum/arxiv-public-datasets"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/routing-networks-and-the-challenges-of","slug":"routing-networks-and-the-challenges-of","title":"Routing Networks and the Challenges of Modular and Compositional Computation","date":"2019-04-29","arxiv_id":"1904.12774","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/routing-networks-and-the-challenges-of#ran","syntology_url":"https://syntology.ai/paper/1904.12774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12774"}},"official":null}},{"url":"/paper/several-experiments-on-investigating","slug":"several-experiments-on-investigating","title":"Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference","date":"2019-04-27","arxiv_id":"1904.12104","repositories_listed":1,"syntology":null},{"url":"/paper/think-again-networks-the-delta-loss-and-an","slug":"think-again-networks-the-delta-loss-and-an","title":"Think Again Networks and the Delta Loss","date":"2019-04-26","arxiv_id":"1904.11816","repositories_listed":1,"syntology":null},{"url":"/paper/190501976","slug":"190501976","title":"TextKD-GAN: Text Generation using KnowledgeDistillation and Generative Adversarial Networks","date":"2019-04-23","arxiv_id":"1905.01976","repositories_listed":1,"syntology":null},{"url":"/paper/good-enough-compositional-data-augmentation","slug":"good-enough-compositional-data-augmentation","title":"Good-Enough Compositional Data Augmentation","date":"2019-04-21","arxiv_id":"1904.09545","repositories_listed":1,"syntology":null},{"url":"/paper/probing-prior-knowledge-needed-in-challenging","slug":"probing-prior-knowledge-needed-in-challenging","title":"Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension","date":"2019-04-21","arxiv_id":"1904.09679","repositories_listed":1,"syntology":null},{"url":"/paper/190409408","slug":"190409408","title":"Language Models with Transformers","date":"2019-04-20","arxiv_id":"1904.09408","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/190409408#ran","syntology_url":"https://syntology.ai/paper/1904.09408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09408"}},"official":{"repos":["cgraywang/gluon-nlp-1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/suggestion-mining-from-online-reviews-using","slug":"suggestion-mining-from-online-reviews-using","title":"Suggestion Mining from Online Reviews using ULMFiT","date":"2019-04-19","arxiv_id":"1904.09076","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-evaluation-of-transformer-language","slug":"dynamic-evaluation-of-transformer-language","title":"Dynamic Evaluation of Transformer Language Models","date":"2019-04-17","arxiv_id":"1904.08378","repositories_listed":1,"syntology":null},{"url":"/paper/effective-estimation-of-deep-generative","slug":"effective-estimation-of-deep-generative","title":"Effective Estimation of Deep Generative Language Models","date":"2019-04-17","arxiv_id":"1904.08194","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/effective-estimation-of-deep-generative#ran","syntology_url":"https://syntology.ai/paper/1904.08194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08194"}},"official":{"repos":["tom-pelsmaeker/deep-generative-lm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sparseout-controlling-sparsity-in-deep","slug":"sparseout-controlling-sparsity-in-deep","title":"Sparseout: Controlling Sparsity in Deep Networks","date":"2019-04-17","arxiv_id":"1904.08050","repositories_listed":1,"syntology":null},{"url":"/paper/sameness-attracts-novelty-disturbs-but","slug":"sameness-attracts-novelty-disturbs-but","title":"Sameness Entices, but Novelty Enchants in Fanfiction Online","date":"2019-04-16","arxiv_id":"1904.07741","repositories_listed":1,"syntology":null},{"url":"/paper/iit-bhu-varanasi-at-msr-srst-2018-a-language-1","slug":"iit-bhu-varanasi-at-msr-srst-2018-a-language-1","title":"IIT (BHU) Varanasi at MSR-SRST 2018: A Language Model Based Approach for Natural Language Generation","date":"2019-04-12","arxiv_id":"1904.06234","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-model-for-joint-chinese-word","slug":"a-unified-model-for-joint-chinese-word","title":"A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing","date":"2019-04-09","arxiv_id":"1904.04697","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-augmented-language-model-and-its","slug":"knowledge-augmented-language-model-and-its","title":"Knowledge-Augmented Language Model and its Application to Unsupervised Named-Entity Recognition","date":"2019-04-09","arxiv_id":"1904.04458","repositories_listed":1,"syntology":null},{"url":"/paper/a-statistical-investigation-of-long-memory-in","slug":"a-statistical-investigation-of-long-memory-in","title":"A Statistical Investigation of Long Memory in Language and Music","date":"2019-04-08","arxiv_id":"1904.03834","repositories_listed":1,"syntology":null},{"url":"/paper/seq3-differentiable-sequence-to-sequence-to","slug":"seq3-differentiable-sequence-to-sequence-to","title":"SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression","date":"2019-04-07","arxiv_id":"1904.03651","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-recurrent-neural-network","slug":"unsupervised-recurrent-neural-network","title":"Unsupervised Recurrent Neural Network Grammars","date":"2019-04-07","arxiv_id":"1904.03746","repositories_listed":1,"syntology":null},{"url":"/paper/alternative-weighting-schemes-for-elmo","slug":"alternative-weighting-schemes-for-elmo","title":"Alternative Weighting Schemes for ELMo Embeddings","date":"2019-04-05","arxiv_id":"1904.02954","repositories_listed":1,"syntology":null},{"url":"/paper/riemannian-normalizing-flow-on-variational","slug":"riemannian-normalizing-flow-on-variational","title":"Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling","date":"2019-04-04","arxiv_id":"1904.02399","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/riemannian-normalizing-flow-on-variational#ran","syntology_url":"https://syntology.ai/paper/1904.02399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02399"}},"official":{"repos":["kingofspace0wzz/wae-rnf-lm"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-domain-adaptation-of","slug":"unsupervised-domain-adaptation-of","title":"Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling","date":"2019-04-04","arxiv_id":"1904.02817","repositories_listed":1,"syntology":null},{"url":"/paper/sart-similarity-analogies-and-relatedness-for","slug":"sart-similarity-analogies-and-relatedness-for","title":"SART - Similarity, Analogies, and Relatedness for Tatar Language: New Benchmark Datasets for Word Embeddings Evaluation","date":"2019-03-31","arxiv_id":"1904.00365","repositories_listed":1,"syntology":null},{"url":"/paper/pre-trained-language-model-representations","slug":"pre-trained-language-model-representations","title":"Pre-trained Language Model Representations for Language Generation","date":"2019-03-22","arxiv_id":"1903.09722","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-sequence-to-sequence-models-for","slug":"evaluating-sequence-to-sequence-models-for","title":"Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition","date":"2019-03-18","arxiv_id":"1903.07377","repositories_listed":1,"syntology":null},{"url":"/paper/the-emergence-of-number-and-syntax-units-in","slug":"the-emergence-of-number-and-syntax-units-in","title":"The emergence of number and syntax units in LSTM language models","date":"2019-03-18","arxiv_id":"1903.07435","repositories_listed":1,"syntology":null},{"url":"/paper/maybe-deep-neural-networks-are-the-best","slug":"maybe-deep-neural-networks-are-the-best","title":"Maybe Deep Neural Networks are the Best Choice for Modeling Source Code","date":"2019-03-13","arxiv_id":"1903.05734","repositories_listed":1,"syntology":null},{"url":"/paper/partially-shuffling-the-training-data-to-1","slug":"partially-shuffling-the-training-data-to-1","title":"Partially Shuffling the Training Data to Improve Language Models","date":"2019-03-11","arxiv_id":"1903.04167","repositories_listed":1,"syntology":null},{"url":"/paper/props-probabilistic-personalization-of-black","slug":"props-probabilistic-personalization-of-black","title":"PROPS: Probabilistic personalization of black-box sequence models","date":"2019-03-05","arxiv_id":"1903.02013","repositories_listed":1,"syntology":null},{"url":"/paper/russian-language-datasets-in-the-digitial","slug":"russian-language-datasets-in-the-digitial","title":"Russian Language Datasets in the Digitial Humanities Domain and Their Evaluation with Word Embeddings","date":"2019-03-04","arxiv_id":"1903.08739","repositories_listed":1,"syntology":null},{"url":"/paper/codegru-context-aware-deep-learning-with","slug":"codegru-context-aware-deep-learning-with","title":"CodeGRU: Context-aware Deep Learning with Gated Recurrent Unit for Source Code Modeling","date":"2019-03-03","arxiv_id":"1903.00884","repositories_listed":1,"syntology":null},{"url":"/paper/alternating-synthetic-and-real-gradients-for","slug":"alternating-synthetic-and-real-gradients-for","title":"Alternating Synthetic and Real Gradients for Neural Language Modeling","date":"2019-02-27","arxiv_id":"1902.10630","repositories_listed":1,"syntology":null},{"url":"/paper/an-embarrassingly-simple-approach-for","slug":"an-embarrassingly-simple-approach-for","title":"An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models","date":"2019-02-27","arxiv_id":"1902.10547","repositories_listed":1,"syntology":null}],"record_sha256":"31f434cfe32be557b2e6599a281755d02be5ca233a36f62b236e975cf5eb79e3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}