{"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/adam/papers/234","list_of":"/method/adam","method":"Adam","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":234,"pages_in_order":244,"rows_per_page":100,"rows":[23301,23400],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/233","next":"/method/adam/papers/235","papers":[{"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":"/paper/towards-simplicity-in-deep-reinforcement-1","slug":"towards-simplicity-in-deep-reinforcement-1","title":"Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling","date":"2019-10-05","arxiv_id":"1910.02208","n_code_links":3,"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":"/paper/quantized-reinforcement-learning-quarl","slug":"quantized-reinforcement-learning-quarl","title":"QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning","date":"2019-10-02","arxiv_id":"1910.01055","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["harvard-edge/quarl"],"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":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":null,"slug":"attribute-manipulation-generative-adversarial","title":"Attribute Manipulation Generative Adversarial Networks for Fashion Images","date":"2019-10-01","arxiv_id":null,"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":"off-policy-multi-step-q-learning","title":"Composite Q-learning: Multi-scale Q-function Decomposition and Separable Optimization","date":"2019-09-30","arxiv_id":"1909.13518","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":"/paper/gacnn-training-deep-convolutional-neural","slug":"gacnn-training-deep-convolutional-neural","title":"GACNN: Training Deep Convolutional Neural Networks with Genetic Algorithm","date":"2019-09-29","arxiv_id":"1909.13354","n_code_links":3,"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":"/paper/high-fidelity-speech-synthesis-with-1","slug":"high-fidelity-speech-synthesis-with-1","title":"High Fidelity Speech Synthesis with Adversarial Networks","date":"2019-09-25","arxiv_id":"1909.11646","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["mbinkowski/DeepSpeechDistances"],"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":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":null,"slug":"constrained-attractor-selection-using-deep","title":"Constrained Attractor Selection Using Deep Reinforcement Learning","date":"2019-09-23","arxiv_id":"1909.10500","n_code_links":0,"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},{"paper":"/paper/allennlp-interpret-a-framework-for-explaining","slug":"allennlp-interpret-a-framework-for-explaining","title":"AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models","date":"2019-09-19","arxiv_id":"1909.09251","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-ways-to-incorporate-additional","title":"How Additional Knowledge can Improve Natural Language Commonsense Question Answering?","date":"2019-09-19","arxiv_id":"1909.08855","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-variational-neural-machine","title":"Improved Variational Neural Machine Translation by Promoting Mutual Information","date":"2019-09-19","arxiv_id":"1909.09237","n_code_links":0,"syntology":null},{"paper":"/paper/summary-level-training-of-sentence-rewriting","slug":"summary-level-training-of-sentence-rewriting","title":"Summary Level Training of Sentence Rewriting for Abstractive Summarization","date":"2019-09-19","arxiv_id":"1909.08752","n_code_links":0,"syntology":null},{"paper":"/paper/enriching-bert-with-knowledge-graph","slug":"enriching-bert-with-knowledge-graph","title":"Enriching BERT with Knowledge Graph Embeddings for Document Classification","date":"2019-09-18","arxiv_id":"1909.08402","n_code_links":1,"syntology":null},{"paper":"/paper/improving-natural-language-inference-with-a","slug":"improving-natural-language-inference-with-a","title":"Improving Natural Language Inference with a Pretrained Parser","date":"2019-09-18","arxiv_id":"1909.08217","n_code_links":1,"syntology":null},{"paper":"/paper/language-models-and-automated-essay-scoring","slug":"language-models-and-automated-essay-scoring","title":"Language models and Automated Essay Scoring","date":"2019-09-18","arxiv_id":"1909.09482","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-bert-for-word-sense-disambiguation","title":"Using BERT for Word Sense Disambiguation","date":"2019-09-18","arxiv_id":"1909.08358","n_code_links":0,"syntology":null},{"paper":"/paper/do-nlp-models-know-numbers-probing-numeracy","slug":"do-nlp-models-know-numbers-probing-numeracy","title":"Do NLP Models Know Numbers? Probing Numeracy in Embeddings","date":"2019-09-17","arxiv_id":"1909.07940","n_code_links":1,"syntology":null},{"paper":"/paper/extracting-evidence-of-supplement-drug","slug":"extracting-evidence-of-supplement-drug","title":"SUPP.AI: Finding Evidence for Supplement-Drug Interactions","date":"2019-09-17","arxiv_id":"1909.08135","n_code_links":1,"syntology":null},{"paper":"/paper/k-bert-enabling-language-representation-with","slug":"k-bert-enabling-language-representation-with","title":"K-BERT: Enabling Language Representation with Knowledge Graph","date":"2019-09-17","arxiv_id":"1909.07606","n_code_links":2,"syntology":null},{"paper":"/paper/megatron-lm-training-multi-billion-parameter","slug":"megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","arxiv_id":"1909.08053","n_code_links":10,"syntology":{"ran":12,"of":47,"n_ran_checked":7,"n_instrument":5,"unverified":35,"pointer_only":15,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 35 unverified","official":{"repos":["NVIDIA/Megatron-LM"],"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":"simple-yet-effective-bridge-reasoning-for","title":"Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering","date":"2019-09-17","arxiv_id":"1909.07597","n_code_links":0,"syntology":null},{"paper":"/paper/span-based-joint-entity-and-relation","slug":"span-based-joint-entity-and-relation","title":"Span-based Joint Entity and Relation Extraction with Transformer Pre-training","date":"2019-09-17","arxiv_id":"1909.07755","n_code_links":3,"syntology":null},{"paper":null,"slug":"a-self-attentional-neural-architecture-for","title":"A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learning","date":"2019-09-16","arxiv_id":"1909.06983","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-neural-models-for-sequence-modelling","title":"Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds","date":"2019-09-16","arxiv_id":"1909.07102","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-neural-machine-translation-for","slug":"multilingual-neural-machine-translation-for","title":"Multilingual Neural Machine Translation for Zero-Resource Languages","date":"2019-09-16","arxiv_id":"1909.07342","n_code_links":1,"syntology":null},{"paper":"/paper/probing-natural-language-inference-models","slug":"probing-natural-language-inference-models","title":"Probing Natural Language Inference Models through Semantic Fragments","date":"2019-09-16","arxiv_id":"1909.07521","n_code_links":3,"syntology":null},{"paper":"/paper/automatically-extracting-challenge-sets-for","slug":"automatically-extracting-challenge-sets-for","title":"Automatically Extracting Challenge Sets for Non local Phenomena in Neural Machine Translation","date":"2019-09-15","arxiv_id":"1909.06814","n_code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-bert-transformation-for-zero","slug":"cross-lingual-bert-transformation-for-zero","title":"Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing","date":"2019-09-15","arxiv_id":"1909.06775","n_code_links":1,"syntology":null},{"paper":null,"slug":"i-mad-a-novel-interpretable-malware-detector","title":"I-MAD: Interpretable Malware Detector Using Galaxy Transformer","date":"2019-09-15","arxiv_id":"1909.06865","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-and-power-evaluation-of-ai","title":"Benchmarking the Performance and Energy Efficiency of AI Accelerators for AI Training","date":"2019-09-15","arxiv_id":"1909.06842","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiency-metrics-for-data-driven-models-a","title":"Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study","date":"2019-09-14","arxiv_id":"1909.06618","n_code_links":0,"syntology":null},{"paper":"/paper/ouroboros-on-accelerating-training-of","slug":"ouroboros-on-accelerating-training-of","title":"Ouroboros: On Accelerating Training of Transformer-Based Language Models","date":"2019-09-14","arxiv_id":"1909.06695","n_code_links":1,"syntology":null},{"paper":"/paper/tree-transformer-integrating-tree-structures","slug":"tree-transformer-integrating-tree-structures","title":"Tree Transformer: Integrating Tree Structures into Self-Attention","date":"2019-09-14","arxiv_id":"1909.06639","n_code_links":3,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"9 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yaushian/Tree-Transformer"],"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/a-comparative-study-on-transformer-vs-rnn-in","slug":"a-comparative-study-on-transformer-vs-rnn-in","title":"A Comparative Study on Transformer vs RNN in Speech Applications","date":"2019-09-13","arxiv_id":"1909.06317","n_code_links":2,"syntology":null},{"paper":"/paper/addressing-semantic-drift-in-question","slug":"addressing-semantic-drift-in-question","title":"Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering","date":"2019-09-13","arxiv_id":"1909.06356","n_code_links":2,"syntology":{"ran":13,"of":19,"n_ran_checked":11,"n_instrument":2,"unverified":6,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["ZhangShiyue/QGforQA"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"neural-machine-translation-with-4-bit","title":"Neural Machine Translation with 4-Bit Precision and Beyond","date":"2019-09-13","arxiv_id":"1909.06091","n_code_links":0,"syntology":null},{"paper":null,"slug":"sanvis-visual-analytics-for-understanding","title":"SANVis: Visual Analytics for Understanding Self-Attention Networks","date":"2019-09-13","arxiv_id":"1909.09595","n_code_links":0,"syntology":null},{"paper":null,"slug":"scene-graph-parsing-by-attention-graph","title":"Scene Graph Parsing by Attention Graph","date":"2019-09-13","arxiv_id":"1909.06273","n_code_links":0,"syntology":null},{"paper":"/paper/towards-open-domain-named-entity-recognition","slug":"towards-open-domain-named-entity-recognition","title":"Neural Correction Model for Open-Domain Named Entity Recognition","date":"2019-09-13","arxiv_id":"1909.06058","n_code_links":1,"syntology":null},{"paper":null,"slug":"cuni-system-for-the-building-educational-1","title":"CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction","date":"2019-09-12","arxiv_id":"1909.05553","n_code_links":0,"syntology":null},{"paper":"/paper/diffgrad-an-optimization-method-for","slug":"diffgrad-an-optimization-method-for","title":"diffGrad: An Optimization Method for Convolutional Neural Networks","date":"2019-09-12","arxiv_id":"1909.11015","n_code_links":1,"syntology":null},{"paper":null,"slug":"measuring-domain-portability-and","title":"Measuring Domain Portability and ErrorPropagation in Biomedical QA","date":"2019-09-12","arxiv_id":"1909.09704","n_code_links":0,"syntology":null},{"paper":"/paper/q-bert-hessian-based-ultra-low-precision","slug":"q-bert-hessian-based-ultra-low-precision","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","date":"2019-09-12","arxiv_id":"1909.05840","n_code_links":0,"syntology":null},{"paper":"/paper/uer-an-open-source-toolkit-for-pre-training","slug":"uer-an-open-source-toolkit-for-pre-training","title":"UER: An Open-Source Toolkit for Pre-training Models","date":"2019-09-12","arxiv_id":"1909.05658","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["dbiir/UER-py"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/bertgrid-contextualized-embedding-for-2d","slug":"bertgrid-contextualized-embedding-for-2d","title":"BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding","date":"2019-09-11","arxiv_id":"1909.04948","n_code_links":2,"syntology":null},{"paper":"/paper/from-english-to-code-switching-transfer","slug":"from-english-to-code-switching-transfer","title":"From English to Code-Switching: Transfer Learning with Strong Morphological Clues","date":"2019-09-11","arxiv_id":"1909.05158","n_code_links":1,"syntology":null},{"paper":"/paper/frustratingly-easy-natural-question-answering","slug":"frustratingly-easy-natural-question-answering","title":"Frustratingly Easy Natural Question Answering","date":"2019-09-11","arxiv_id":"1909.05286","n_code_links":0,"syntology":null},{"paper":null,"slug":"global-locality-in-event-extraction","title":"Global Locality in Biomedical Relation and Event Extraction","date":"2019-09-11","arxiv_id":"1909.04822","n_code_links":0,"syntology":null},{"paper":"/paper/how-does-bert-answer-questions-a-layer-wise","slug":"how-does-bert-answer-questions-a-layer-wise","title":"How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations","date":"2019-09-11","arxiv_id":"1909.04925","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["bvanaken/explain-BERT-QA"],"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":["official"]}}},{"paper":null,"slug":"boltzmann-machine-learning-and-regularization","title":"Boltzmann machine learning and regularization methods for inferring evolutionary fields and couplings from a multiple sequence alignment","date":"2019-09-10","arxiv_id":"1909.05006","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-stochastic-quasi-newton-method-with","title":"A Stochastic Quasi-Newton Method with Nesterov's Accelerated Gradient","date":"2019-09-09","arxiv_id":"1909.03621","n_code_links":0,"syntology":null}],"record_sha256":"2c2957d3b37fb5ab5c2870ab5acf00e8c9ade10ba6b064c19ad4ec07db00ed5a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}