{"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":"/method/attention/papers/312","list_of":"/method/attention","method":"Attention","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":312,"pages_in_order":316,"rows_per_page":100,"rows":[31101,31200],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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":"/method/attention","prev":"/method/attention/papers/311","next":"/method/attention/papers/313","papers":[{"paper":"/paper/a-neural-grammatical-error-correction-system","slug":"a-neural-grammatical-error-correction-system","title":"A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learning","date":"2019-07-02","arxiv_id":"1907.01256","n_code_links":2,"syntology":null},{"paper":"/paper/multimodal-transformer-networks-for-end-to","slug":"multimodal-transformer-networks-for-end-to","title":"Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems","date":"2019-07-02","arxiv_id":"1907.01166","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["henryhungle/MTN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/predicting-retrosynthetic-reaction-using-self","slug":"predicting-retrosynthetic-reaction-using-self","title":"Predicting Retrosynthetic Reaction using Self-Corrected Transformer Neural Networks","date":"2019-07-02","arxiv_id":"1907.01356","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-and-effective-approach-to-automatic-1","slug":"a-simple-and-effective-approach-to-automatic-1","title":"A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-surprisingly-robust-trick-for-the-winograd","title":"A Surprisingly Robust Trick for the Winograd Schema Challenge","date":"2019-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-over-heads-a-multi-hop-attention","title":"Attention over Heads: A Multi-Hop Attention for Neural Machine Translation","date":"2019-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/bert-based-lexical-substitution","slug":"bert-based-lexical-substitution","title":"BERT-based Lexical Substitution","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/complex-question-decomposition-for-semantic","slug":"complex-question-decomposition-for-semantic","title":"Complex Question Decomposition for Semantic Parsing","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/coreference-resolution-with-entity","slug":"coreference-resolution-with-entity","title":"Coreference Resolution with Entity Equalization","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/dissent-learning-sentence-representations","slug":"dissent-learning-sentence-representations","title":"DisSent: Learning Sentence Representations from Explicit Discourse Relations","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"do-transformer-attention-heads-provide","title":"Do Transformer Attention Heads Provide Transparency in Abstractive Summarization?","date":"2019-07-01","arxiv_id":"1907.00570","n_code_links":0,"syntology":null},{"paper":null,"slug":"english-indonesian-neural-machine-translation","title":"English-Indonesian Neural Machine Translation for Spoken Language Domains","date":"2019-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-pre-trained-language","slug":"enhancing-pre-trained-language","title":"Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"global-transformer-u-nets-for-label-free","title":"Global Pixel Transformers for Virtual Staining of Microscopy Images","date":"2019-07-01","arxiv_id":"1907.00941","n_code_links":0,"syntology":null},{"paper":"/paper/literary-event-detection","slug":"literary-event-detection","title":"Literary Event Detection","date":"2019-07-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"multilingual-multi-scale-and-multi-layer","title":"Multilingual, Multi-scale and Multi-layer Visualization of Intermediate Representations","date":"2019-07-01","arxiv_id":"1907.00810","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-machine-translation-with-reordering","title":"Neural Machine Translation with Reordering Embeddings","date":"2019-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neuralclassifier-an-open-source-neural","title":"NeuralClassifier: An Open-source Neural Hierarchical Multi-label Text Classification Toolkit","date":"2019-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"patent-claim-generation-by-fine-tuning-openai","title":"Patent Claim Generation by Fine-Tuning OpenAI GPT-2","date":"2019-07-01","arxiv_id":"1907.02052","n_code_links":0,"syntology":null},{"paper":null,"slug":"pentagon-at-mediqa-2019-multi-task-learning","title":"Pentagon at MEDIQA 2019: Multi-task Learning for Filtering and Re-ranking Answers using Language Inference and Question Entailment","date":"2019-07-01","arxiv_id":"1907.01643","n_code_links":0,"syntology":null},{"paper":"/paper/t-cvae-transformer-based-conditioned","slug":"t-cvae-transformer-based-conditioned","title":"T-CVAE: Transformer-Based Conditioned Variational Autoencoder for Story Completion","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/using-database-rule-for-weak-supervised-text","slug":"using-database-rule-for-weak-supervised-text","title":"Using Database Rule for Weak Supervised Text-to-SQL Generation","date":"2019-07-01","arxiv_id":"1907.00620","n_code_links":2,"syntology":null},{"paper":"/paper/what-does-bert-learn-about-the-structure-of","slug":"what-does-bert-learn-about-the-structure-of","title":"What Does BERT Learn about the Structure of Language?","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/xqa-a-cross-lingual-open-domain-question","slug":"xqa-a-cross-lingual-open-domain-question","title":"XQA: A Cross-lingual Open-domain Question Answering Dataset","date":"2019-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"you-only-need-attention-to-traverse-trees","title":"You Only Need Attention to Traverse Trees","date":"2019-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-language-model-finetuning","slug":"evaluating-language-model-finetuning","title":"Evaluating Language Model Finetuning Techniques for Low-resource Languages","date":"2019-06-30","arxiv_id":"1907.00409","n_code_links":2,"syntology":null},{"paper":"/paper/the-university-of-sydneys-machine-translation","slug":"the-university-of-sydneys-machine-translation","title":"The University of Sydney's Machine Translation System for WMT19","date":"2019-06-30","arxiv_id":"1907.00494","n_code_links":0,"syntology":null},{"paper":"/paper/empirical-evaluation-of-sequence-to-sequence","slug":"empirical-evaluation-of-sequence-to-sequence","title":"Empirical Evaluation of Sequence-to-Sequence Models for Word Discovery in Low-resource Settings","date":"2019-06-29","arxiv_id":"1907.00184","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-the-locality-and-breaking-the","slug":"enhancing-the-locality-and-breaking-the","title":"Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting","date":"2019-06-29","arxiv_id":"1907.00235","n_code_links":2,"syntology":null},{"paper":"/paper/gpt-based-generation-for-classical-chinese","slug":"gpt-based-generation-for-classical-chinese","title":"GPT-based Generation for Classical Chinese Poetry","date":"2019-06-29","arxiv_id":"1907.00151","n_code_links":3,"syntology":null},{"paper":null,"slug":"localizing-unseen-activities-in-video-via","title":"Localizing Unseen Activities in Video via Image Query","date":"2019-06-28","arxiv_id":"1906.12165","n_code_links":0,"syntology":null},{"paper":"/paper/widening-the-representation-bottleneck-in","slug":"widening-the-representation-bottleneck-in","title":"Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts","date":"2019-06-28","arxiv_id":"1906.12284","n_code_links":1,"syntology":null},{"paper":"/paper/compositional-semantic-parsing-across","slug":"compositional-semantic-parsing-across","title":"Compositional Semantic Parsing Across Graphbanks","date":"2019-06-27","arxiv_id":"1906.11746","n_code_links":1,"syntology":null},{"paper":null,"slug":"inducing-syntactic-trees-from-bert","title":"Inducing Syntactic Trees from BERT Representations","date":"2019-06-27","arxiv_id":"1906.11511","n_code_links":0,"syntology":null},{"paper":"/paper/relating-simple-sentence-representations-in","slug":"relating-simple-sentence-representations-in","title":"Relating Simple Sentence Representations in Deep Neural Networks and the Brain","date":"2019-06-27","arxiv_id":"1906.11861","n_code_links":1,"syntology":null},{"paper":null,"slug":"sharing-attention-weights-for-fast","title":"Sharing Attention Weights for Fast Transformer","date":"2019-06-26","arxiv_id":"1906.11024","n_code_links":0,"syntology":null},{"paper":"/paper/spatial-transformer-for-3d-points","slug":"spatial-transformer-for-3d-points","title":"Spatial Transformer for 3D Point Clouds","date":"2019-06-26","arxiv_id":"1906.10887","n_code_links":1,"syntology":null},{"paper":"/paper/saliency-driven-word-alignment-interpretation","slug":"saliency-driven-word-alignment-interpretation","title":"Saliency-driven Word Alignment Interpretation for Neural Machine Translation","date":"2019-06-25","arxiv_id":"1906.10282","n_code_links":1,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","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":[]}}},{"paper":null,"slug":"self-multi-head-attention-for-speaker","title":"Self Multi-Head Attention for Speaker Recognition","date":"2019-06-24","arxiv_id":"1906.09890","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-generation-from-both-sides-to-the","title":"Sequence Generation: From Both Sides to the Middle","date":"2019-06-23","arxiv_id":"1906.09601","n_code_links":0,"syntology":null},{"paper":"/paper/learning-set-equivariant-functions-with-swarm","slug":"learning-set-equivariant-functions-with-swarm","title":"Learning Set-equivariant Functions with SWARM Mappings","date":"2019-06-22","arxiv_id":"1906.09400","n_code_links":1,"syntology":null},{"paper":"/paper/retrieving-sequential-information-for-non","slug":"retrieving-sequential-information-for-non","title":"Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation","date":"2019-06-22","arxiv_id":"1906.09444","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ictnlp/RSI-NAT"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"cuni-system-for-the-wmt19-robustness-task","title":"CUNI System for the WMT19 Robustness Task","date":"2019-06-21","arxiv_id":"1906.09246","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-named-entity-recognition-using-1","slug":"multilingual-named-entity-recognition-using-1","title":"Multilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF","date":"2019-06-21","arxiv_id":"1906.09978","n_code_links":2,"syntology":null},{"paper":null,"slug":"improving-zero-shot-translation-with-language","title":"Improving Zero-shot Translation with Language-Independent Constraints","date":"2019-06-20","arxiv_id":"1906.08584","n_code_links":0,"syntology":null},{"paper":null,"slug":"informative-image-captioning-with-external","title":"Informative Image Captioning with External Sources of Information","date":"2019-06-20","arxiv_id":"1906.08876","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-multi-domain-adaptation","title":"Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation","date":"2019-06-19","arxiv_id":"1906.07978","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-with-whole-word-masking-for","slug":"pre-training-with-whole-word-masking-for","title":"Pre-Training with Whole Word Masking for Chinese BERT","date":"2019-06-19","arxiv_id":"1906.08101","n_code_links":2,"syntology":null},{"paper":null,"slug":"transfer-nas-knowledge-transfer-between","title":"Transfer NAS: Knowledge Transfer between Search Spaces with Transformer Agents","date":"2019-06-19","arxiv_id":"1906.08102","n_code_links":0,"syntology":null},{"paper":"/paper/xlnet-generalized-autoregressive-pretraining","slug":"xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","n_code_links":27,"syntology":{"ran":15,"of":24,"n_ran_checked":10,"n_instrument":5,"unverified":9,"pointer_only":4,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified","official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/measuring-bias-in-contextualized-word","slug":"measuring-bias-in-contextualized-word","title":"Measuring Bias in Contextualized Word Representations","date":"2019-06-18","arxiv_id":"1906.07337","n_code_links":1,"syntology":null},{"paper":"/paper/scheduled-sampling-for-transformers","slug":"scheduled-sampling-for-transformers","title":"Scheduled Sampling for Transformers","date":"2019-06-18","arxiv_id":"1906.07651","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["deep-spin/scheduled-sampling-transformers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/transfer-learning-for-causal-sentence","slug":"transfer-learning-for-causal-sentence","title":"Transfer Learning for Causal Sentence Detection","date":"2019-06-18","arxiv_id":"1906.07544","n_code_links":2,"syntology":null},{"paper":"/paper/zero-shot-entity-linking-by-reading-entity","slug":"zero-shot-entity-linking-by-reading-entity","title":"Zero-Shot Entity Linking by Reading Entity Descriptions","date":"2019-06-18","arxiv_id":"1906.07348","n_code_links":3,"syntology":null},{"paper":null,"slug":"exploiting-unsupervised-pre-training-and","title":"Exploiting Unsupervised Pre-training and Automated Feature Engineering for Low-resource Hate Speech Detection in Polish","date":"2019-06-17","arxiv_id":"1906.09325","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-transfer-learning-for-end-to-end","title":"Towards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Models","date":"2019-06-17","arxiv_id":"1906.07307","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-epoch-is-all-you-need","title":"One Epoch Is All You Need","date":"2019-06-16","arxiv_id":"1906.06669","n_code_links":0,"syntology":null},{"paper":"/paper/context-is-key-grammatical-error-detection","slug":"context-is-key-grammatical-error-detection","title":"Context is Key: Grammatical Error Detection with Contextual Word Representations","date":"2019-06-15","arxiv_id":"1906.06593","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-and-effective-approach-to-automatic","slug":"a-simple-and-effective-approach-to-automatic","title":"A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning","date":"2019-06-14","arxiv_id":"1906.06253","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["deep-spin/OpenNMT-APE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/image-captioning-transforming-objects-into","slug":"image-captioning-transforming-objects-into","title":"Image Captioning: Transforming Objects into Words","date":"2019-06-14","arxiv_id":"1906.05963","n_code_links":4,"syntology":{"ran":9,"of":10,"n_ran_checked":4,"n_instrument":5,"unverified":1,"pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yahoo/object_relation_transformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"contrastive-bidirectional-transformer-for","title":"Learning Video Representations using Contrastive Bidirectional Transformer","date":"2019-06-13","arxiv_id":"1906.05743","n_code_links":0,"syntology":null},{"paper":null,"slug":"lattice-transformer-for-speech-translation","title":"Lattice Transformer for Speech Translation","date":"2019-06-13","arxiv_id":"1906.05551","n_code_links":0,"syntology":null},{"paper":null,"slug":"telephonetic-making-neural-language-models","title":"Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise","date":"2019-06-13","arxiv_id":"1906.05678","n_code_links":0,"syntology":null},{"paper":"/paper/temporal-transformer-networks-joint-learning-1","slug":"temporal-transformer-networks-joint-learning-1","title":"Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping","date":"2019-06-13","arxiv_id":"1906.05947","n_code_links":1,"syntology":null},{"paper":"/paper/a-multiscale-visualization-of-attention-in","slug":"a-multiscale-visualization-of-attention-in","title":"A Multiscale Visualization of Attention in the Transformer Model","date":"2019-06-12","arxiv_id":"1906.05714","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["jessevig/bertviz"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/neural-arabic-question-answering","slug":"neural-arabic-question-answering","title":"Neural Arabic Question Answering","date":"2019-06-12","arxiv_id":"1906.05394","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["husseinmozannar/SOQAL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/synthetic-qa-corpora-generation-with","slug":"synthetic-qa-corpora-generation-with","title":"Synthetic QA Corpora Generation with Roundtrip Consistency","date":"2019-06-12","arxiv_id":"1906.05416","n_code_links":4,"syntology":null},{"paper":null,"slug":"cuedwmt19ewclms","title":"Cued@wmt19:ewc&lms","date":"2019-06-11","arxiv_id":"1906.05447","n_code_links":0,"syntology":null},{"paper":"/paper/explicit-disentanglement-of-appearance-and","slug":"explicit-disentanglement-of-appearance-and","title":"Explicit Disentanglement of Appearance and Perspective in Generative Models","date":"2019-06-11","arxiv_id":"1906.11881","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-fully-supervised-to-zero-shot-settings","title":"From Fully Supervised to Zero Shot Settings for Twitter Hashtag Recommendation","date":"2019-06-11","arxiv_id":"1906.04914","n_code_links":0,"syntology":null},{"paper":"/paper/graph-convolutional-transformer-learning-the","slug":"graph-convolutional-transformer-learning-the","title":"Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer","date":"2019-06-11","arxiv_id":"1906.04716","n_code_links":2,"syntology":null},{"paper":"/paper/lightweight-and-efficient-neural-natural","slug":"lightweight-and-efficient-neural-natural","title":"Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks","date":"2019-06-11","arxiv_id":"1906.04393","n_code_links":1,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","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":[]}}},{"paper":"/paper/learning-to-combine-grammatical-error","slug":"learning-to-combine-grammatical-error","title":"Learning to combine Grammatical Error Corrections","date":"2019-06-10","arxiv_id":"1906.03897","n_code_links":1,"syntology":null},{"paper":null,"slug":"patch-transformer-for-multi-tagging-whole","title":"Patch Transformer for Multi-tagging Whole Slide Histopathology Images","date":"2019-06-10","arxiv_id":"1906.04151","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-university-of-helsinki-submissions-to-the-1","title":"The University of Helsinki submissions to the WMT19 news translation task","date":"2019-06-10","arxiv_id":"1906.04040","n_code_links":0,"syntology":null},{"paper":"/paper/cross-view-semantic-segmentation-for-sensing","slug":"cross-view-semantic-segmentation-for-sensing","title":"Cross-view Semantic Segmentation for Sensing Surroundings","date":"2019-06-09","arxiv_id":"1906.03560","n_code_links":1,"syntology":null},{"paper":"/paper/gendered-pronoun-resolution-using-bert-and-an","slug":"gendered-pronoun-resolution-using-bert-and-an","title":"Gendered Pronoun Resolution using BERT and an extractive question answering formulation","date":"2019-06-09","arxiv_id":"1906.03695","n_code_links":1,"syntology":null},{"paper":null,"slug":"making-asynchronous-stochastic-gradient","title":"Making Asynchronous Stochastic Gradient Descent Work for Transformers","date":"2019-06-08","arxiv_id":"1906.03496","n_code_links":0,"syntology":null},{"paper":"/paper/sentence-centrality-revisited-for","slug":"sentence-centrality-revisited-for","title":"Sentence Centrality Revisited for Unsupervised Summarization","date":"2019-06-08","arxiv_id":"1906.03508","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-the-structure-of-attention-in-a","title":"Analyzing the Structure of Attention in a Transformer Language Model","date":"2019-06-07","arxiv_id":"1906.04284","n_code_links":0,"syntology":null},{"paper":"/paper/improving-relation-extraction-by-pre-trained-1","slug":"improving-relation-extraction-by-pre-trained-1","title":"Improving Relation Extraction by Pre-trained Language Representations","date":"2019-06-07","arxiv_id":"1906.03088","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-bert-for-extractive-text","slug":"leveraging-bert-for-extractive-text","title":"Leveraging BERT for Extractive Text Summarization on Lectures","date":"2019-06-07","arxiv_id":"1906.04165","n_code_links":8,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-is-all-you-need-for-videos-self","title":"Attention is all you need for Videos: Self-attention based Video Summarization using Universal Transformers","date":"2019-06-06","arxiv_id":"1906.02792","n_code_links":0,"syntology":null},{"paper":"/paper/gcdt-a-global-context-enhanced-deep","slug":"gcdt-a-global-context-enhanced-deep","title":"GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling","date":"2019-06-06","arxiv_id":"1906.02437","n_code_links":1,"syntology":null},{"paper":null,"slug":"playing-the-lottery-with-rewards-and-multiple","title":"Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP","date":"2019-06-06","arxiv_id":"1906.02768","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-neural-machine-translation-with-doubly","title":"Robust Neural Machine Translation with Doubly Adversarial Inputs","date":"2019-06-06","arxiv_id":"1906.02443","n_code_links":0,"syntology":null},{"paper":"/paper/syntactically-supervised-transformers-for","slug":"syntactically-supervised-transformers-for","title":"Syntactically Supervised Transformers for Faster Neural Machine Translation","date":"2019-06-06","arxiv_id":"1906.02780","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dojoteef/synst"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-and-improving-transformer-from","slug":"understanding-and-improving-transformer-from","title":"Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View","date":"2019-06-06","arxiv_id":"1906.02762","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":8,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhuohan123/macaron-net"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/visualizing-and-measuring-the-geometry-of","slug":"visualizing-and-measuring-the-geometry-of","title":"Visualizing and Measuring the Geometry of BERT","date":"2019-06-06","arxiv_id":"1906.02715","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-balustrades-to-pierre-vinken-looking-for","title":"From Balustrades to Pierre Vinken: Looking for Syntax in Transformer Self-Attentions","date":"2019-06-05","arxiv_id":"1906.01958","n_code_links":0,"syntology":null},{"paper":"/paper/large-scale-multi-label-text-classification-1","slug":"large-scale-multi-label-text-classification-1","title":"Large-Scale Multi-Label Text Classification on EU Legislation","date":"2019-06-05","arxiv_id":"1906.02192","n_code_links":1,"syntology":null},{"paper":"/paper/learning-deep-transformer-models-for-machine","slug":"learning-deep-transformer-models-for-machine","title":"Learning Deep Transformer Models for Machine Translation","date":"2019-06-05","arxiv_id":"1906.01787","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 3 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; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["wangqiangneu/dlcl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/neural-legal-judgment-prediction-in-english","slug":"neural-legal-judgment-prediction-in-english","title":"Neural Legal Judgment Prediction in English","date":"2019-06-05","arxiv_id":"1906.02059","n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-hypergraph-grammars-for","title":"Probabilistic hypergraph grammars for efficient molecular optimization","date":"2019-06-05","arxiv_id":"1906.01845","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploiting-sentential-context-for-neural","title":"Exploiting Sentential Context for Neural Machine Translation","date":"2019-06-04","arxiv_id":"1906.01268","n_code_links":0,"syntology":null},{"paper":"/paper/how-multilingual-is-multilingual-bert","slug":"how-multilingual-is-multilingual-bert","title":"How multilingual is Multilingual BERT?","date":"2019-06-04","arxiv_id":"1906.01502","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":null}}],"record_sha256":"aaec50f51584b2f851086b92ecbf1aee0604292ddbb25a1c1a000a4fb76592c3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}