{"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/308","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":308,"pages_in_order":316,"rows_per_page":100,"rows":[30701,30800],"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/307","next":"/method/attention/papers/309","papers":[{"paper":null,"slug":"predicting-retrosynthetic-pathways-using-a","title":"Predicting retrosynthetic pathways using a combined linguistic model and hyper-graph exploration strategy","date":"2019-10-17","arxiv_id":"1910.08036","n_code_links":0,"syntology":null},{"paper":"/paper/question-classification-with-deep","slug":"question-classification-with-deep","title":"Question Classification with Deep Contextualized Transformer","date":"2019-10-17","arxiv_id":"1910.10492","n_code_links":1,"syntology":null},{"paper":null,"slug":"universal-text-representation-from-bert-an","title":"Universal Text Representation from BERT: An Empirical Study","date":"2019-10-17","arxiv_id":"1910.07973","n_code_links":0,"syntology":null},{"paper":"/paper/bertram-improved-word-embeddings-have-big","slug":"bertram-improved-word-embeddings-have-big","title":"BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance","date":"2019-10-16","arxiv_id":"1910.07181","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["timoschick/bertram"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bridging-the-knowledge-gap-enhancing-question","title":"Bridging the Knowledge Gap: Enhancing Question Answering with World and Domain Knowledge","date":"2019-10-16","arxiv_id":"1910.07429","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiency-through-auto-sizing-notre-dame","title":"Efficiency through Auto-Sizing: Notre Dame NLP's Submission to the WNGT 2019 Efficiency Task","date":"2019-10-16","arxiv_id":"1910.07134","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolution-of-transfer-learning-in-natural","title":"Evolution of transfer learning in natural language processing","date":"2019-10-16","arxiv_id":"1910.07370","n_code_links":0,"syntology":null},{"paper":null,"slug":"imperial-college-london-submission-to-vatex","title":"Imperial College London Submission to VATEX Video Captioning Task","date":"2019-10-16","arxiv_id":"1910.07482","n_code_links":0,"syntology":null},{"paper":"/paper/injecting-hierarchy-with-u-net-transformers","slug":"injecting-hierarchy-with-u-net-transformers","title":"Injecting Hierarchy with U-Net Transformers","date":"2019-10-16","arxiv_id":"1910.10488","n_code_links":2,"syntology":null},{"paper":null,"slug":"mix-review-alleviate-forgetting-in-the","title":"Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models","date":"2019-10-16","arxiv_id":"1910.07117","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-asr-with-contextual-block","title":"Transformer ASR with Contextual Block Processing","date":"2019-10-16","arxiv_id":"1910.07204","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-whole-document-context-in-neural","title":"Using Whole Document Context in Neural Machine Translation","date":"2019-10-16","arxiv_id":"1910.07481","n_code_links":0,"syntology":null},{"paper":"/paper/aligning-cross-lingual-entities-with-multi","slug":"aligning-cross-lingual-entities-with-multi","title":"Aligning Cross-Lingual Entities with Multi-Aspect Information","date":"2019-10-15","arxiv_id":"1910.06575","n_code_links":1,"syntology":null},{"paper":"/paper/answering-complex-open-domain-questions","slug":"answering-complex-open-domain-questions","title":"Answering Complex Open-domain Questions Through Iterative Query Generation","date":"2019-10-15","arxiv_id":"1910.07000","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qipeng/golden-retriever"],"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"]}}},{"paper":"/paper/enhancing-the-transformer-with-explicit-1","slug":"enhancing-the-transformer-with-explicit-1","title":"Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving","date":"2019-10-15","arxiv_id":"1910.06611","n_code_links":3,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ischlag/TP-Transformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"facebook-ais-wat19-myanmar-english","title":"Facebook AI's WAT19 Myanmar-English Translation Task Submission","date":"2019-10-15","arxiv_id":"1910.06848","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-a-bert-based-question-answering-model","title":"Structured Pruning of a BERT-based Question Answering Model","date":"2019-10-14","arxiv_id":"1910.06360","n_code_links":0,"syntology":null},{"paper":"/paper/q8bert-quantized-8bit-bert","slug":"q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","arxiv_id":"1910.06188","n_code_links":5,"syntology":{"ran":10,"of":11,"n_ran_checked":9,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["intellabs/model-compression-research-package","NervanaSystems/nlp-architect"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/stancy-stance-classification-based-on","slug":"stancy-stance-classification-based-on","title":"STANCY: Stance Classification Based on Consistency Cues","date":"2019-10-14","arxiv_id":"1910.06048","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-without-tears-improving-the","slug":"transformers-without-tears-improving-the","title":"Transformers without Tears: Improving the Normalization of Self-Attention","date":"2019-10-14","arxiv_id":"1910.05895","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tnq177/transformers_without_tears"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/whatcha-lookin-at-deeplifting-berts-attention","slug":"whatcha-lookin-at-deeplifting-berts-attention","title":"Whatcha lookin' at? DeepLIFTing BERT's Attention in Question Answering","date":"2019-10-14","arxiv_id":"1910.06431","n_code_links":1,"syntology":null},{"paper":null,"slug":"progress-notes-classification-and-keyword","title":"Progress Notes Classification and Keyword Extraction using Attention-based Deep Learning Models with BERT","date":"2019-10-13","arxiv_id":"1910.05786","n_code_links":0,"syntology":null},{"paper":"/paper/stabilizing-transformers-for-reinforcement-1","slug":"stabilizing-transformers-for-reinforcement-1","title":"Stabilizing Transformers for Reinforcement Learning","date":"2019-10-13","arxiv_id":"1910.06764","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/vq-wav2vec-self-supervised-learning-of-1","slug":"vq-wav2vec-self-supervised-learning-of-1","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","date":"2019-10-12","arxiv_id":"1910.05453","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"automatic-segmentation-of-texts-into-units-of","title":"Automatic segmentation of texts into units of meaning for reading assistance","date":"2019-10-11","arxiv_id":"1910.05014","n_code_links":0,"syntology":null},{"paper":"/paper/bipar-a-bilingual-parallel-dataset-for","slug":"bipar-a-bilingual-parallel-dataset-for","title":"BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels","date":"2019-10-11","arxiv_id":"1910.05040","n_code_links":1,"syntology":null},{"paper":"/paper/exbert-a-visual-analysis-tool-to-explore","slug":"exbert-a-visual-analysis-tool-to-explore","title":"exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models","date":"2019-10-11","arxiv_id":"1910.05276","n_code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-alignment-vs-joint-training-a","slug":"cross-lingual-alignment-vs-joint-training-a","title":"Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework","date":"2019-10-10","arxiv_id":"1910.04708","n_code_links":2,"syntology":null},{"paper":"/paper/fuse-multi-faceted-set-expansion-by-coherent","slug":"fuse-multi-faceted-set-expansion-by-coherent","title":"FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams","date":"2019-10-10","arxiv_id":"1910.04345","n_code_links":3,"syntology":null},{"paper":"/paper/multi-label-categorization-of-accounts-of","slug":"multi-label-categorization-of-accounts-of","title":"Multi-label Categorization of Accounts of Sexism using a Neural Framework","date":"2019-10-10","arxiv_id":"1910.04602","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-question-answering-from","title":"Multilingual Question Answering from Formatted Text applied to Conversational Agents","date":"2019-10-10","arxiv_id":"1910.04659","n_code_links":0,"syntology":null},{"paper":"/paper/on-recognizing-texts-of-arbitrary-shapes-with","slug":"on-recognizing-texts-of-arbitrary-shapes-with","title":"On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention","date":"2019-10-10","arxiv_id":"1910.04396","n_code_links":2,"syntology":null},{"paper":null,"slug":"orthogonality-constrained-multi-head","title":"Orthogonality Constrained Multi-Head Attention For Keyword Spotting","date":"2019-10-10","arxiv_id":"1910.04500","n_code_links":0,"syntology":null},{"paper":"/paper/structured-pruning-of-large-language-models","slug":"structured-pruning-of-large-language-models","title":"Structured Pruning of Large Language Models","date":"2019-10-10","arxiv_id":"1910.04732","n_code_links":2,"syntology":{"ran":8,"of":12,"n_ran_checked":6,"n_instrument":2,"unverified":4,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["asappresearch/flop"],"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/visual-natural-language-query-auto-completion","slug":"visual-natural-language-query-auto-completion","title":"Visual Natural Language Query Auto-Completion for Estimating Instance Probabilities","date":"2019-10-10","arxiv_id":"1910.04887","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-closer-look-at-feature-space-data","title":"A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification","date":"2019-10-09","arxiv_id":"1910.04176","n_code_links":0,"syntology":null},{"paper":"/paper/alternating-recurrent-dialog-model-with-large","slug":"alternating-recurrent-dialog-model-with-large","title":"Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models","date":"2019-10-09","arxiv_id":"1910.03756","n_code_links":1,"syntology":null},{"paper":"/paper/is-multilingual-bert-fluent-in-language","slug":"is-multilingual-bert-fluent-in-language","title":"Is Multilingual BERT Fluent in Language Generation?","date":"2019-10-09","arxiv_id":"1910.03806","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-adequacy-of-untuned-warmup-for","slug":"on-the-adequacy-of-untuned-warmup-for","title":"On the adequacy of untuned warmup for adaptive optimization","date":"2019-10-09","arxiv_id":"1910.04209","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/pipemare-asynchronous-pipeline-parallel-dnn","slug":"pipemare-asynchronous-pipeline-parallel-dnn","title":"PipeMare: Asynchronous Pipeline Parallel DNN Training","date":"2019-10-09","arxiv_id":"1910.05124","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-state-of-the-art-natural","slug":"transformers-state-of-the-art-natural","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","date":"2019-10-09","arxiv_id":"1910.03771","n_code_links":9,"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":["huggingface/transformers"],"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"]}}},{"paper":null,"slug":"knowledge-distillation-from-internal","title":"Knowledge Distillation from Internal Representations","date":"2019-10-08","arxiv_id":"1910.03723","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-simultaneous-forecasting-of","title":"Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting","date":"2019-10-08","arxiv_id":"1910.03650","n_code_links":0,"syntology":null},{"paper":null,"slug":"sesamebert-attention-for-anywhere","title":"SesameBERT: Attention for Anywhere","date":"2019-10-08","arxiv_id":"1910.03176","n_code_links":0,"syntology":null},{"paper":"/paper/bert-for-evidence-retrieval-and-claim","slug":"bert-for-evidence-retrieval-and-claim","title":"BERT for Evidence Retrieval and Claim Verification","date":"2019-10-07","arxiv_id":"1910.02655","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":0,"n_instrument":4,"unverified":2,"pointer_only":6,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/parallel-iterative-edit-models-for-local","slug":"parallel-iterative-edit-models-for-local","title":"Parallel Iterative Edit Models for Local Sequence Transduction","date":"2019-10-07","arxiv_id":"1910.02893","n_code_links":1,"syntology":null},{"paper":null,"slug":"smart-training-shallow-memory-aware","title":"SMArT: Training Shallow Memory-aware Transformers for Robotic Explainability","date":"2019-10-07","arxiv_id":"1910.02974","n_code_links":0,"syntology":null},{"paper":"/paper/named-entity-recognition-is-there-a-glass","slug":"named-entity-recognition-is-there-a-glass","title":"Named Entity Recognition -- Is there a glass ceiling?","date":"2019-10-06","arxiv_id":"1910.02403","n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-based-fault-tolerant-approach-for","title":"Attention-based Fault-tolerant Approach for Multi-agent Reinforcement Learning Systems","date":"2019-10-05","arxiv_id":"1910.02240","n_code_links":0,"syntology":null},{"paper":"/paper/how-transformer-revitalizes-character-based","slug":"how-transformer-revitalizes-character-based","title":"How Transformer Revitalizes Character-based Neural Machine Translation: An Investigation on Japanese-Vietnamese Translation Systems","date":"2019-10-05","arxiv_id":"1910.02238","n_code_links":1,"syntology":null},{"paper":null,"slug":"distilling-transformers-into-simple-neural","title":"Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data","date":"2019-10-04","arxiv_id":"1910.01769","n_code_links":0,"syntology":null},{"paper":"/paper/fine-grained-sentiment-classification-using","slug":"fine-grained-sentiment-classification-using","title":"Fine-grained Sentiment Classification using BERT","date":"2019-10-04","arxiv_id":"1910.03474","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":null}},{"paper":"/paper/zero-memory-optimization-towards-training-a","slug":"zero-memory-optimization-towards-training-a","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","date":"2019-10-04","arxiv_id":"1910.02054","n_code_links":10,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["NVIDIA/Megatron-LM","microsoft/DeepSpeed"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/towards-understanding-of-medical-randomized","slug":"towards-understanding-of-medical-randomized","title":"Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generation","date":"2019-10-03","arxiv_id":"1910.01462","n_code_links":1,"syntology":null},{"paper":null,"slug":"cracking-the-contextual-commonsense-code","title":"Cracking the Contextual Commonsense Code: Understanding Commonsense Reasoning Aptitude of Deep Contextual Representations","date":"2019-10-02","arxiv_id":"1910.01157","n_code_links":0,"syntology":null},{"paper":"/paper/distilbert-a-distilled-version-of-bert","slug":"distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","n_code_links":37,"syntology":{"ran":21,"of":27,"n_ran_checked":13,"n_instrument":8,"unverified":6,"pointer_only":2,"phrase":"21 ran (of which 5 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified","official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"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":["listed","official"]}}},{"paper":"/paper/exploiting-bert-for-end-to-end-aspect-based","slug":"exploiting-bert-for-end-to-end-aspect-based","title":"Exploiting BERT for End-to-End Aspect-based Sentiment Analysis","date":"2019-10-02","arxiv_id":"1910.00883","n_code_links":1,"syntology":null},{"paper":"/paper/linking-artificial-and-human-neural","slug":"linking-artificial-and-human-neural","title":"Linking artificial and human neural representations of language","date":"2019-10-02","arxiv_id":"1910.01244","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":4,"n_instrument":4,"unverified":3,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"application-of-low-resource-machine","title":"Application of Low-resource Machine Translation Techniques to Russian-Tatar Language Pair","date":"2019-10-01","arxiv_id":"1910.00368","n_code_links":0,"syntology":null},{"paper":"/paper/auto-sizing-the-transformer-network-improving","slug":"auto-sizing-the-transformer-network-improving","title":"Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation","date":"2019-10-01","arxiv_id":"1910.06717","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-for-question-generation","title":"BERT for Question Generation","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dialogue-transformers","slug":"dialogue-transformers","title":"Dialogue Transformers","date":"2019-10-01","arxiv_id":"1910.00486","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficiency-metrics-for-data-driven-models-a-1","title":"Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"entangled-transformer-for-image-captioning","title":"Entangled Transformer for Image Captioning","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/grammatical-error-correction-in-low-resource","slug":"grammatical-error-correction-in-low-resource","title":"Grammatical Error Correction in Low-Resource Scenarios","date":"2019-10-01","arxiv_id":"1910.00353","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/specializing-word-embeddings-for-parsing-by","slug":"specializing-word-embeddings-for-parsing-by","title":"Specializing Word Embeddings (for Parsing) by Information Bottleneck","date":"2019-10-01","arxiv_id":"1910.00163","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"vae-pgn-based-abstractive-model-in-multi","title":"VAE-PGN based Abstractive Model in Multi-stage Architecture for Text Summarization","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-resume-parsing-and-finding","title":"End-to-End Resume Parsing and Finding Candidates for a Job Description using BERT","date":"2019-09-30","arxiv_id":"1910.03089","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-head-attention-with-diversity-for","title":"Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations","date":"2019-09-30","arxiv_id":"1910.00058","n_code_links":0,"syntology":null},{"paper":"/paper/fake-news-detection-using-deep-learning","slug":"fake-news-detection-using-deep-learning","title":"Fake news detection using Deep Learning","date":"2019-09-29","arxiv_id":"1910.03496","n_code_links":2,"syntology":null},{"paper":null,"slug":"gdp-generalized-device-placement-for-dataflow","title":"GDP: Generalized Device Placement for Dataflow Graphs","date":"2019-09-28","arxiv_id":"1910.01578","n_code_links":0,"syntology":null},{"paper":"/paper/hatemonitors-language-agnostic-abuse","slug":"hatemonitors-language-agnostic-abuse","title":"HateMonitors: Language Agnostic Abuse Detection in Social Media","date":"2019-09-27","arxiv_id":"1909.12642","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-use-of-bert-for-neural-machine","title":"On the use of BERT for Neural Machine Translation","date":"2019-09-27","arxiv_id":"1909.12744","n_code_links":0,"syntology":null},{"paper":null,"slug":"reweighted-proximal-pruning-for-large-scale-1","title":"Reweighted Proximal Pruning for Large-Scale Language Representation","date":"2019-09-27","arxiv_id":"1909.12486","n_code_links":0,"syntology":null},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","n_code_links":48,"syntology":{"ran":81,"of":126,"n_ran_checked":59,"n_instrument":22,"unverified":45,"pointer_only":28,"phrase":"81 ran (of which 17 constructed an object rather than computing a result; 59 with no instrument failure: 4 honoured, 0 violated, 55 with no contract checked; 22 where Syntology's instrument failed) · 45 unverified","official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"aspect-and-opinion-term-extraction-for-aspect","title":"Aspect and Opinion Term Extraction for Hotel Reviews using Transfer Learning and Auxiliary Labels","date":"2019-09-26","arxiv_id":"1909.11879","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-pre-trained-multilingual-models","title":"Improving Pre-Trained Multilingual Models with Vocabulary Expansion","date":"2019-09-26","arxiv_id":"1909.12440","n_code_links":0,"syntology":null},{"paper":"/paper/monotonic-multihead-attention-1","slug":"monotonic-multihead-attention-1","title":"Monotonic Multihead Attention","date":"2019-09-26","arxiv_id":"1909.12406","n_code_links":3,"syntology":null},{"paper":"/paper/unsupervised-universal-self-attention-network","slug":"unsupervised-universal-self-attention-network","title":"Universal Graph Transformer Self-Attention Networks","date":"2019-09-26","arxiv_id":"1909.11855","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["daiquocnguyen/Graph-Transformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/attention-convolutional-binary-neural-tree","slug":"attention-convolutional-binary-neural-tree","title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","date":"2019-09-25","arxiv_id":"1909.11378","n_code_links":2,"syntology":null},{"paper":null,"slug":"extreme-language-model-compression-with-1","title":"Extremely Small BERT Models from Mixed-Vocabulary Training","date":"2019-09-25","arxiv_id":"1909.11687","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-detect-opinion-snippet-for-aspect","title":"Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis","date":"2019-09-25","arxiv_id":"1909.11297","n_code_links":0,"syntology":null},{"paper":"/paper/mixout-effective-regularization-to-finetune","slug":"mixout-effective-regularization-to-finetune","title":"Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models","date":"2019-09-25","arxiv_id":"1909.11299","n_code_links":2,"syntology":null},{"paper":"/paper/reducing-transformer-depth-on-demand-with-1","slug":"reducing-transformer-depth-on-demand-with-1","title":"Reducing Transformer Depth on Demand with Structured Dropout","date":"2019-09-25","arxiv_id":"1909.11556","n_code_links":5,"syntology":null},{"paper":"/paper/knowledge-enriched-transformer-for-emotion","slug":"knowledge-enriched-transformer-for-emotion","title":"Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations","date":"2019-09-24","arxiv_id":"1909.10681","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"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":["zhongpeixiang/KET"],"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"]}}},{"paper":null,"slug":"technical-report-on-conversational-question","title":"Technical report on Conversational Question Answering","date":"2019-09-24","arxiv_id":"1909.10772","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-across-languages-from","title":"Efficiently Reusing Old Models Across Languages via Transfer Learning","date":"2019-09-24","arxiv_id":"1909.10955","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-semantics-from-speech-through","title":"Understanding Semantics from Speech Through Pre-training","date":"2019-09-24","arxiv_id":"1909.10924","n_code_links":0,"syntology":null},{"paper":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","n_code_links":3,"syntology":{"ran":11,"of":14,"n_ran_checked":8,"n_instrument":3,"unverified":3,"pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","n_code_links":10,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":"/paper/190910430","slug":"190910430","title":"Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings","date":"2019-09-23","arxiv_id":"1909.10430","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-identification-and-normalisation-of","slug":"automatic-identification-and-normalisation-of","title":"Automatic Identification and Normalisation of Physical Measurements in Scientific Literature","date":"2019-09-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/portuguese-named-entity-recognition-using-1","slug":"portuguese-named-entity-recognition-using-1","title":"Portuguese Named Entity Recognition using BERT-CRF","date":"2019-09-23","arxiv_id":"1909.10649","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["neuralmind-ai/portuguese-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"190909779","title":"Self-attention based end-to-end Hindi-English Neural Machine Translation","date":"2019-09-21","arxiv_id":"1909.09779","n_code_links":0,"syntology":null},{"paper":null,"slug":"190909801","title":"Adversarial Learning of General Transformations for Data Augmentation","date":"2019-09-21","arxiv_id":"1909.09801","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-meets-chinese-word-segmentation","title":"BERT Meets Chinese Word Segmentation","date":"2019-09-20","arxiv_id":"1909.09292","n_code_links":0,"syntology":null}],"record_sha256":"09679d0ceca5da1e351bcb053166bed088d24ceee57978807ae9ff7df2104d83","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}