{"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/absolute-position-encodings/papers/127","list_of":"/method/absolute-position-encodings","method":"Absolute Position Encodings","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":127,"pages_in_order":140,"rows_per_page":100,"rows":[12601,12700],"of":13942,"counts":{"archive_papers_tagged":13942,"with_a_code_link":6505,"where_syntology_ran_a_sample":2224,"not_listed_spam_title":0,"listed":13942,"listed_where_code_ran":2224,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1897,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1897,"listed_every_run_a_failure_of_syntologys_instrument":327,"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/absolute-position-encodings","prev":"/method/absolute-position-encodings/papers/126","next":"/method/absolute-position-encodings/papers/128","papers":[{"paper":"/paper/bangla-text-classification-using-transformers","slug":"bangla-text-classification-using-transformers","title":"Bangla Text Classification using Transformers","date":"2020-11-09","arxiv_id":"2011.04446","n_code_links":1,"syntology":null},{"paper":"/paper/magneto-an-efficient-deep-learning-method-for-1","slug":"magneto-an-efficient-deep-learning-method-for-1","title":"MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization Problem","date":"2020-11-09","arxiv_id":"2011.04349","n_code_links":1,"syntology":null},{"paper":"/paper/visbert-hidden-state-visualizations-for","slug":"visbert-hidden-state-visualizations-for","title":"VisBERT: Hidden-State Visualizations for Transformers","date":"2020-11-09","arxiv_id":"2011.04507","n_code_links":1,"syntology":null},{"paper":"/paper/long-range-arena-a-benchmark-for-efficient-1","slug":"long-range-arena-a-benchmark-for-efficient-1","title":"Long Range Arena: A Benchmark for Efficient Transformers","date":"2020-11-08","arxiv_id":"2011.04006","n_code_links":5,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/long-range-arena"],"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/stochastic-attention-head-removal-a-simple","slug":"stochastic-attention-head-removal-a-simple","title":"Stochastic Attention Head Removal: A simple and effective method for improving Transformer Based ASR Models","date":"2020-11-08","arxiv_id":"2011.04004","n_code_links":5,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["s1603602/attention_head_removal"],"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":"know-what-you-don-t-need-single-shot-meta","title":"Know What You Don't Need: Single-Shot Meta-Pruning for Attention Heads","date":"2020-11-07","arxiv_id":"2011.03770","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-the-value-of-transformer","title":"Rethinking the Value of Transformer Components","date":"2020-11-07","arxiv_id":"2011.03803","n_code_links":0,"syntology":null},{"paper":"/paper/from-dataset-recycling-to-multi-property","slug":"from-dataset-recycling-to-multi-property","title":"From Dataset Recycling to Multi-Property Extraction and Beyond","date":"2020-11-06","arxiv_id":"2011.03228","n_code_links":1,"syntology":null},{"paper":null,"slug":"bw-eda-eend-streaming-end-to-end-neural","title":"BW-EDA-EEND: Streaming End-to-End Neural Speaker Diarization for a Variable Number of Speakers","date":"2020-11-05","arxiv_id":"2011.02678","n_code_links":0,"syntology":null},{"paper":"/paper/indic-transformers-an-analysis-of-transformer","slug":"indic-transformers-an-analysis-of-transformer","title":"Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages","date":"2020-11-04","arxiv_id":"2011.02323","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-transformer-for-low-resource","title":"Optimizing Transformer for Low-Resource Neural Machine Translation","date":"2020-11-04","arxiv_id":"2011.02266","n_code_links":0,"syntology":null},{"paper":"/paper/dual-decoder-transformer-for-joint-automatic","slug":"dual-decoder-transformer-for-joint-automatic","title":"Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation","date":"2020-11-02","arxiv_id":"2011.00747","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-far-does-bert-look-at-distance-based","title":"How Far Does BERT Look At:Distance-based Clustering and Analysis of BERT$'$s Attention","date":"2020-11-02","arxiv_id":"2011.00943","n_code_links":0,"syntology":null},{"paper":"/paper/point-transformer","slug":"point-transformer","title":"Point Transformer","date":"2020-11-02","arxiv_id":"2011.00931","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 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":["engelnico/point-transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"active-learning-approaches-to-enhancing","title":"Active Learning Approaches to Enhancing Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/approximation-of-response-knowledge-retrieval","slug":"approximation-of-response-knowledge-retrieval","title":"Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"context-analysis-for-pre-trained-masked","title":"Context Analysis for Pre-trained Masked Language Models","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/coot-cooperative-hierarchical-transformer-for","slug":"coot-cooperative-hierarchical-transformer-for","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","date":"2020-11-01","arxiv_id":"2011.00597","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["gingsi/coot-videotext"],"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":["official"]}}},{"paper":null,"slug":"factorized-transformer-for-multi-domain","title":"Factorized Transformer for Multi-Domain Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/kermit-complementing-transformer","slug":"kermit-complementing-transformer","title":"KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/multi-2oie-multilingual-open-information-1","slug":"multi-2oie-multilingual-open-information-1","title":"Multi\\^2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"smrt-chatbots-improving-non-task-oriented","title":"SMRT Chatbots: Improving Non-Task-Oriented Dialog with Simulated Multiple Reference Training","date":"2020-11-01","arxiv_id":"2011.00547","n_code_links":0,"syntology":null},{"paper":"/paper/social-chemistry-101-learning-to-reason-about","slug":"social-chemistry-101-learning-to-reason-about","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","date":"2020-11-01","arxiv_id":"2011.00620","n_code_links":2,"syntology":null},{"paper":"/paper/generating-radiology-reports-via-memory","slug":"generating-radiology-reports-via-memory","title":"Generating Radiology Reports via Memory-driven Transformer","date":"2020-10-30","arxiv_id":"2010.16056","n_code_links":2,"syntology":{"ran":26,"of":31,"n_ran_checked":20,"n_instrument":6,"unverified":5,"pointer_only":25,"phrase":"26 ran (of which 13 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 3 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","official":{"repos":["zhjohnchan/R2Gen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","official"]}}},{"paper":"/paper/veco-variable-encoder-decoder-pre-training-1","slug":"veco-variable-encoder-decoder-pre-training-1","title":"VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation","date":"2020-10-30","arxiv_id":"2010.16046","n_code_links":1,"syntology":null},{"paper":null,"slug":"memory-attentive-fusion-external-language","title":"Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model","date":"2020-10-29","arxiv_id":"2010.15437","n_code_links":0,"syntology":null},{"paper":null,"slug":"tilde-at-wmt-2020-news-task-systems","title":"Tilde at WMT 2020: News Task Systems","date":"2020-10-29","arxiv_id":"2010.15423","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-unknot","title":"Learning to Unknot","date":"2020-10-28","arxiv_id":"2010.16263","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-volctrans-machine-translation-system-for","title":"The Volctrans Machine Translation System for WMT20","date":"2020-10-28","arxiv_id":"2010.14806","n_code_links":0,"syntology":null},{"paper":"/paper/fast-interleaved-bidirectional-sequence","slug":"fast-interleaved-bidirectional-sequence","title":"Fast Interleaved Bidirectional Sequence Generation","date":"2020-10-27","arxiv_id":"2010.14481","n_code_links":1,"syntology":null},{"paper":"/paper/fragmentvc-any-to-any-voice-conversion-by-end","slug":"fragmentvc-any-to-any-voice-conversion-by-end","title":"FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention","date":"2020-10-27","arxiv_id":"2010.14150","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["yistLin/FragmentVC"],"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/mmft-bert-multimodal-fusion-transformer-with","slug":"mmft-bert-multimodal-fusion-transformer-with","title":"MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering","date":"2020-10-27","arxiv_id":"2010.14095","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-emotion-recognition-with","slug":"multimodal-emotion-recognition-with","title":"Multimodal Emotion Recognition with Transformer-Based Self Supervised Feature Fusion","date":"2020-10-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/controlled-molecule-generator-for-optimizing","slug":"controlled-molecule-generator-for-optimizing","title":"Controlled Molecule Generator for Optimizing Multiple Chemical Properties","date":"2020-10-26","arxiv_id":"2010.13908","n_code_links":1,"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":["deargen/cmg"],"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/fastformers-highly-efficient-transformer","slug":"fastformers-highly-efficient-transformer","title":"FastFormers: Highly Efficient Transformer Models for Natural Language Understanding","date":"2020-10-26","arxiv_id":"2010.13382","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["microsoft/fastformers"],"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":"graph-transformer-networks-with-syntactic-and","title":"Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction","date":"2020-10-26","arxiv_id":"2010.13391","n_code_links":0,"syntology":null},{"paper":null,"slug":"peak-detection-on-data-independent","title":"Peak Detection On Data Independent Acquisition Mass Spectrometry Data With Semisupervised Convolutional Transformers","date":"2020-10-26","arxiv_id":"2010.13841","n_code_links":0,"syntology":null},{"paper":"/paper/effective-distant-supervision-for-temporal","slug":"effective-distant-supervision-for-temporal","title":"Effective Distant Supervision for Temporal Relation Extraction","date":"2020-10-24","arxiv_id":"2010.12755","n_code_links":2,"syntology":null},{"paper":"/paper/hierarchical-transformer-for-task-oriented","slug":"hierarchical-transformer-for-task-oriented","title":"Hierarchical Transformer for Task Oriented Dialog Systems","date":"2020-10-24","arxiv_id":"2011.08067","n_code_links":2,"syntology":null},{"paper":null,"slug":"open-domain-dialogue-generation-based-on-pre","title":"Open-Domain Dialogue Generation Based on Pre-trained Language Models","date":"2020-10-24","arxiv_id":"2010.12780","n_code_links":0,"syntology":null},{"paper":"/paper/pre-trained-summarization-distillation","slug":"pre-trained-summarization-distillation","title":"Pre-trained Summarization Distillation","date":"2020-10-24","arxiv_id":"2010.13002","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-embedding-coupling-in-pre-trained-1","slug":"rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","date":"2020-10-24","arxiv_id":"2010.12821","n_code_links":4,"syntology":null},{"paper":null,"slug":"a-pre-training-strategy-for-recommendation","title":"Pre-training Graph Transformer with Multimodal Side Information for Recommendation","date":"2020-10-23","arxiv_id":"2010.12284","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-approach-for-handling-out-of","slug":"a-simple-approach-for-handling-out-of","title":"A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code","date":"2020-10-23","arxiv_id":"2010.12663","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-framework-for-measuring-the","slug":"deep-learning-framework-for-measuring-the","title":"Deep Learning Framework for Measuring the Digital Strategy of Companies from Earnings Calls","date":"2020-10-23","arxiv_id":"2010.12418","n_code_links":1,"syntology":null},{"paper":"/paper/don-t-shoot-butterfly-with-rifles-multi","slug":"don-t-shoot-butterfly-with-rifles-multi","title":"Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer","date":"2020-10-23","arxiv_id":"2010.12180","n_code_links":1,"syntology":null},{"paper":null,"slug":"graphspeech-syntax-aware-graph-attention","title":"GraphSpeech: Syntax-Aware Graph Attention Network For Neural Speech Synthesis","date":"2020-10-23","arxiv_id":"2010.12423","n_code_links":0,"syntology":null},{"paper":"/paper/lightseq-a-high-performance-inference-library","slug":"lightseq-a-high-performance-inference-library","title":"LightSeq: A High Performance Inference Library for Transformers","date":"2020-10-23","arxiv_id":"2010.13887","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-transformer-growth-for-progressive","title":"On the Transformer Growth for Progressive BERT Training","date":"2020-10-23","arxiv_id":"2010.12562","n_code_links":0,"syntology":null},{"paper":null,"slug":"stabilizing-transformer-based-action-sequence","title":"Stabilizing Transformer-Based Action Sequence Generation For Q-Learning","date":"2020-10-23","arxiv_id":"2010.12698","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-end-to-end-speech","slug":"transformer-based-end-to-end-speech","title":"Transformer-based End-to-End Speech Recognition with Local Dense Synthesizer Attention","date":"2020-10-23","arxiv_id":"2010.12155","n_code_links":1,"syntology":null},{"paper":"/paper/an-image-is-worth-16x16-words-transformers-1","slug":"an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","arxiv_id":"2010.11929","n_code_links":158,"syntology":{"ran":307,"of":419,"n_ran_checked":286,"n_instrument":21,"unverified":112,"pointer_only":154,"phrase":"307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified","official":{"repos":["google-research/vision_transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["community","listed","unlocated"]}}},{"paper":null,"slug":"developing-real-time-streaming-transformer","title":"Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset","date":"2020-10-22","arxiv_id":"2010.11395","n_code_links":0,"syntology":null},{"paper":"/paper/how-phonotactics-affect-multilingual-and-zero","slug":"how-phonotactics-affect-multilingual-and-zero","title":"How Phonotactics Affect Multilingual and Zero-shot ASR Performance","date":"2020-10-22","arxiv_id":"2010.12104","n_code_links":1,"syntology":null},{"paper":"/paper/n-ode-transformer-a-depth-adaptive-variant-of","slug":"n-ode-transformer-a-depth-adaptive-variant-of","title":"N-ODE Transformer: A Depth-Adaptive Variant of the Transformer Using Neural Ordinary Differential Equations","date":"2020-10-22","arxiv_id":"2010.11358","n_code_links":1,"syntology":null},{"paper":"/paper/analyzing-the-source-and-target-contributions","slug":"analyzing-the-source-and-target-contributions","title":"Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation","date":"2020-10-21","arxiv_id":"2010.10907","n_code_links":1,"syntology":null},{"paper":"/paper/generalized-conditioned-dialogue-generation","slug":"generalized-conditioned-dialogue-generation","title":"A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation","date":"2020-10-21","arxiv_id":"2010.11140","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-domain-dialogue-state-tracking-based-on-1","title":"Multi-Domain Dialogue State Tracking based on State Graph","date":"2020-10-21","arxiv_id":"2010.11137","n_code_links":0,"syntology":null},{"paper":"/paper/multi-unit-transformer-for-neural-machine","slug":"multi-unit-transformer-for-neural-machine","title":"Multi-Unit Transformers for Neural Machine Translation","date":"2020-10-21","arxiv_id":"2010.10743","n_code_links":1,"syntology":null},{"paper":null,"slug":"tmt-a-transformer-based-modal-translator-for","title":"TMT: A Transformer-based Modal Translator for Improving Multimodal Sequence Representations in Audio Visual Scene-aware Dialog","date":"2020-10-21","arxiv_id":"2010.10839","n_code_links":0,"syntology":null},{"paper":"/paper/token-drop-mechanism-for-neural-machine","slug":"token-drop-mechanism-for-neural-machine","title":"Token Drop mechanism for Neural Machine Translation","date":"2020-10-21","arxiv_id":"2010.11018","n_code_links":1,"syntology":null},{"paper":"/paper/wavetransformer-a-novel-architecture-for","slug":"wavetransformer-a-novel-architecture-for","title":"WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information","date":"2020-10-21","arxiv_id":"2010.11098","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert2dnn-bert-distillation-with-massive","title":"BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search","date":"2020-10-20","arxiv_id":"2010.10442","n_code_links":0,"syntology":null},{"paper":"/paper/bootleg-chasing-the-tail-with-self-supervised","slug":"bootleg-chasing-the-tail-with-self-supervised","title":"Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation","date":"2020-10-20","arxiv_id":"2010.10363","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":null}},{"paper":"/paper/characterbert-reconciling-elmo-and-bert-for","slug":"characterbert-reconciling-elmo-and-bert-for","title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","date":"2020-10-20","arxiv_id":"2010.10392","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":4,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["helboukkouri/character-bert"],"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/privacy-preserving-visual-content-tagging","slug":"privacy-preserving-visual-content-tagging","title":"Privacy-Preserving Visual Content Tagging using Graph Transformer Networks","date":"2020-10-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/privacy-preserving-visual-content-tagging-1","slug":"privacy-preserving-visual-content-tagging-1","title":"Privacy-Preserving Visual Content Tagging using Graph Transformer Networks","date":"2020-10-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/prop-pre-training-with-representative-words","slug":"prop-pre-training-with-representative-words","title":"PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval","date":"2020-10-20","arxiv_id":"2010.10137","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-scalable-distributed-training-of-deep","title":"Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters","date":"2020-10-20","arxiv_id":"2010.10458","n_code_links":0,"syntology":null},{"paper":"/paper/transition-based-parsing-with-stack","slug":"transition-based-parsing-with-stack","title":"Transition-based Parsing with Stack-Transformers","date":"2020-10-20","arxiv_id":"2010.10669","n_code_links":1,"syntology":null},{"paper":"/paper/infusing-sequential-information-into","slug":"infusing-sequential-information-into","title":"Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism","date":"2020-10-19","arxiv_id":"2010.09194","n_code_links":1,"syntology":null},{"paper":null,"slug":"query-aware-tip-generation-for-vertical","title":"Query-aware Tip Generation for Vertical Search","date":"2020-10-19","arxiv_id":"2010.09254","n_code_links":0,"syntology":null},{"paper":"/paper/saint-integrating-temporal-features-for-ednet","slug":"saint-integrating-temporal-features-for-ednet","title":"SAINT+: Integrating Temporal Features for EdNet Correctness Prediction","date":"2020-10-19","arxiv_id":"2010.12042","n_code_links":4,"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: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/capturing-longer-context-for-document-level","slug":"capturing-longer-context-for-document-level","title":"Rethinking Document-level Neural Machine Translation","date":"2020-10-18","arxiv_id":"2010.08961","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":["sunzewei2715/Doc2Doc_NMT"],"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":"cross-lingual-relation-extraction-with","title":"Cross-Lingual Relation Extraction with Transformers","date":"2020-10-16","arxiv_id":"2010.08652","n_code_links":0,"syntology":null},{"paper":null,"slug":"didi-s-machine-translation-system-for-wmt2020","title":"DiDi's Machine Translation System for WMT2020","date":"2020-10-16","arxiv_id":"2010.08185","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-token-level-uncertainty-to-learn","title":"Modeling Token-level Uncertainty to Learn Unknown Concepts in SLU via Calibrated Dirichlet Prior RNN","date":"2020-10-16","arxiv_id":"2010.08101","n_code_links":0,"syntology":null},{"paper":"/paper/towards-natural-bilingual-and-code-switched","slug":"towards-natural-bilingual-and-code-switched","title":"Towards Natural Bilingual and Code-Switched Speech Synthesis Based on Mix of Monolingual Recordings and Cross-Lingual Voice Conversion","date":"2020-10-16","arxiv_id":"2010.08136","n_code_links":1,"syntology":null},{"paper":"/paper/compressive-summarization-with-plausibility","slug":"compressive-summarization-with-plausibility","title":"Compressive Summarization with Plausibility and Salience Modeling","date":"2020-10-15","arxiv_id":"2010.07886","n_code_links":1,"syntology":{"ran":15,"of":17,"n_ran_checked":3,"n_instrument":12,"unverified":2,"pointer_only":17,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 2 unverified","official":{"repos":["shreydesai/cups"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/context-guided-bert-for-targeted-aspect-based","slug":"context-guided-bert-for-targeted-aspect-based","title":"Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis","date":"2020-10-15","arxiv_id":"2010.07523","n_code_links":1,"syntology":null},{"paper":null,"slug":"dialoguetrm-exploring-the-intra-and-inter","title":"DialogueTRM: Exploring the Intra- and Inter-Modal Emotional Behaviors in the Conversation","date":"2020-10-15","arxiv_id":"2010.07637","n_code_links":0,"syntology":null},{"paper":"/paper/empirical-study-of-transformers-for-source","slug":"empirical-study-of-transformers-for-source","title":"Empirical Study of Transformers for Source Code","date":"2020-10-15","arxiv_id":"2010.07987","n_code_links":1,"syntology":null},{"paper":"/paper/masked-contrastive-representation-learning","slug":"masked-contrastive-representation-learning","title":"Masked Contrastive Representation Learning for Reinforcement Learning","date":"2020-10-15","arxiv_id":"2010.07470","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["teslacool/m-curl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-task-learning-for-cross-lingual","title":"Multi-Task Learning for Cross-Lingual Abstractive Summarization","date":"2020-10-15","arxiv_id":"2010.07503","n_code_links":0,"syntology":null},{"paper":"/paper/natural-language-rationales-with-full-stack","slug":"natural-language-rationales-with-full-stack","title":"Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs","date":"2020-10-15","arxiv_id":"2010.07526","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-optical-flow-estimation-in-360","title":"Revisiting Optical Flow Estimation in 360 Videos","date":"2020-10-15","arxiv_id":"2010.08045","n_code_links":0,"syntology":null},{"paper":null,"slug":"da-transformer-distance-aware-transformer","title":"DA-Transformer: Distance-aware Transformer","date":"2020-10-14","arxiv_id":"2010.06925","n_code_links":0,"syntology":null},{"paper":"/paper/length-adaptive-transformer-train-once-with-1","slug":"length-adaptive-transformer-train-once-with-1","title":"Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search","date":"2020-10-14","arxiv_id":"2010.07003","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"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) · 0 unverified","official":{"repos":["clovaai/length-adaptive-transformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"memformer-the-memory-augmented-transformer-1","title":"Memformer: A Memory-Augmented Transformer for Sequence Modeling","date":"2020-10-14","arxiv_id":"2010.06891","n_code_links":0,"syntology":null},{"paper":"/paper/aspect-based-document-similarity-for-research","slug":"aspect-based-document-similarity-for-research","title":"Aspect-based Document Similarity for Research Papers","date":"2020-10-13","arxiv_id":"2010.06395","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["malteos/aspect-document-similarity"],"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":null,"slug":"context-aware-drive-thru-recommendation","title":"Context-Aware Drive-thru Recommendation Service at Fast Food Restaurants","date":"2020-10-13","arxiv_id":"2010.06197","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpreting-attention-models-with-human","title":"Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension","date":"2020-10-13","arxiv_id":"2010.06396","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-memory-enhanced-transformer-for-end","slug":"dynamic-memory-enhanced-transformer-for-end","title":"Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems","date":"2020-10-12","arxiv_id":"2010.05740","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-pretrained-language-models-for","title":"Probing Pretrained Language Models for Lexical Semantics","date":"2020-10-12","arxiv_id":"2010.05731","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-translation-of-mathematical-text","title":"Machine Translation of Mathematical Text","date":"2020-10-11","arxiv_id":"2010.05229","n_code_links":0,"syntology":null},{"paper":null,"slug":"information-extraction-from-swedish-medical","title":"Information Extraction from Swedish Medical Prescriptions with Sig-Transformer Encoder","date":"2020-10-10","arxiv_id":"2010.04897","n_code_links":0,"syntology":null},{"paper":"/paper/structured-self-attention-weights-encode","slug":"structured-self-attention-weights-encode","title":"Structured Self-Attention Weights Encode Semantics in Sentiment Analysis","date":"2020-10-10","arxiv_id":"2010.04922","n_code_links":1,"syntology":null},{"paper":"/paper/on-task-level-dialogue-composition-of","slug":"on-task-level-dialogue-composition-of","title":"On Task-Level Dialogue Composition of Generative Transformer Model","date":"2020-10-09","arxiv_id":"2010.04826","n_code_links":1,"syntology":null},{"paper":"/paper/online-back-parsing-for-amr-to-text","slug":"online-back-parsing-for-amr-to-text","title":"Online Back-Parsing for AMR-to-Text Generation","date":"2020-10-09","arxiv_id":"2010.04520","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-nu-voice-conversion-system-for-the-voice","title":"The NU Voice Conversion System for the Voice Conversion Challenge 2020: On the Effectiveness of Sequence-to-sequence Models and Autoregressive Neural Vocoders","date":"2020-10-09","arxiv_id":"2010.04446","n_code_links":0,"syntology":null}],"record_sha256":"96a1bd191a149ab7d3ed12465a3dcd79173dc8b436600553aab1a323d2f9fdad","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}