{"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/bpe/papers/177","list_of":"/method/bpe","method":"BPE","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":177,"pages_in_order":190,"rows_per_page":100,"rows":[17601,17700],"of":18975,"counts":{"archive_papers_tagged":18975,"with_a_code_link":8675,"where_syntology_ran_a_sample":2895,"not_listed_spam_title":0,"listed":18975,"listed_where_code_ran":2895,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2443,"every_run_a_failure_of_syntologys_instrument":452,"listed_with_a_run_with_no_instrument_failure":2443,"listed_every_run_a_failure_of_syntologys_instrument":452,"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/bpe","prev":"/method/bpe/papers/176","next":"/method/bpe/papers/178","papers":[{"paper":"/paper/modern-methods-for-text-generation","slug":"modern-methods-for-text-generation","title":"Modern Methods for Text Generation","date":"2020-09-10","arxiv_id":"2009.04968","n_code_links":2,"syntology":null},{"paper":"/paper/rank-over-class-the-untapped-potential-of","slug":"rank-over-class-the-untapped-potential-of","title":"Rank over Class: The Untapped Potential of Ranking in Natural Language Processing","date":"2020-09-10","arxiv_id":"2009.05160","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["atapour/rank-over-class"],"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":"/paper/sparsifying-transformer-models-with","slug":"sparsifying-transformer-models-with","title":"Sparsifying Transformer Models with Trainable Representation Pooling","date":"2020-09-10","arxiv_id":"2009.05169","n_code_links":1,"syntology":null},{"paper":null,"slug":"central-yup-ik-and-machine-translation-of-low","title":"Central Yup'ik and Machine Translation of Low-Resource Polysynthetic Languages","date":"2020-09-09","arxiv_id":"2009.04087","n_code_links":0,"syntology":null},{"paper":"/paper/pay-attention-when-required","slug":"pay-attention-when-required","title":"Pay Attention when Required","date":"2020-09-09","arxiv_id":"2009.04534","n_code_links":2,"syntology":null},{"paper":"/paper/masked-label-prediction-unified-massage","slug":"masked-label-prediction-unified-massage","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","date":"2020-09-08","arxiv_id":"2009.03509","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["PaddlePaddle/PGL"],"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":["listed","official"]}}},{"paper":"/paper/adversarial-watermarking-transformer-towards","slug":"adversarial-watermarking-transformer-towards","title":"Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding","date":"2020-09-07","arxiv_id":"2009.03015","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"black-box-to-white-box-discover-model","title":"Black Box to White Box: Discover Model Characteristics Based on Strategic Probing","date":"2020-09-07","arxiv_id":"2009.03136","n_code_links":0,"syntology":null},{"paper":"/paper/improving-language-generation-with-sentence","slug":"improving-language-generation-with-sentence","title":"Improving Language Generation with Sentence Coherence Objective","date":"2020-09-07","arxiv_id":"2009.06358","n_code_links":1,"syntology":null},{"paper":"/paper/measuring-massive-multitask-language","slug":"measuring-massive-multitask-language","title":"Measuring Massive Multitask Language Understanding","date":"2020-09-07","arxiv_id":"2009.03300","n_code_links":18,"syntology":{"ran":19,"of":26,"n_ran_checked":15,"n_instrument":4,"unverified":7,"pointer_only":1,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["hendrycks/test"],"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":"robust-conversational-ai-with-grounded-text","title":"Robust Conversational AI with Grounded Text Generation","date":"2020-09-07","arxiv_id":"2009.03457","n_code_links":0,"syntology":null},{"paper":"/paper/transmodality-an-end2end-fusion-method-with","slug":"transmodality-an-end2end-fusion-method-with","title":"TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis","date":"2020-09-07","arxiv_id":"2009.02902","n_code_links":0,"syntology":null},{"paper":null,"slug":"edinburghnlp-at-wnut-2020-task-2-leveraging","title":"EdinburghNLP at WNUT-2020 Task 2: Leveraging Transformers with Generalized Augmentation for Identifying Informativeness in COVID-19 Tweets","date":"2020-09-06","arxiv_id":"2009.06375","n_code_links":0,"syntology":null},{"paper":null,"slug":"qiaoning-at-semeval-2020-task-4-commonsense","title":"QiaoNing at SemEval-2020 Task 4: Commonsense Validation and Explanation system based on ensemble of language model","date":"2020-09-06","arxiv_id":"2009.02645","n_code_links":0,"syntology":null},{"paper":null,"slug":"voice-conversion-by-cascading-automatic","title":"Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody Transfer","date":"2020-09-03","arxiv_id":"2009.01475","n_code_links":0,"syntology":null},{"paper":"/paper/comparative-evaluation-of-pretrained-transfer","slug":"comparative-evaluation-of-pretrained-transfer","title":"Comparative Evaluation of Pretrained Transfer Learning Models on Automatic Short Answer Grading","date":"2020-09-02","arxiv_id":"2009.01303","n_code_links":1,"syntology":null},{"paper":"/paper/liftformer-3d-human-pose-estimation-using","slug":"liftformer-3d-human-pose-estimation-using","title":"LiftFormer: 3D Human Pose Estimation using attention models","date":"2020-09-01","arxiv_id":"2009.00348","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallel-rescoring-with-transformer-for","title":"Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition","date":"2020-08-30","arxiv_id":"2008.13093","n_code_links":0,"syntology":null},{"paper":"/paper/hitter-hierarchical-transformers-for","slug":"hitter-hierarchical-transformers-for","title":"HittER: Hierarchical Transformers for Knowledge Graph Embeddings","date":"2020-08-28","arxiv_id":"2008.12813","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"knowledge-efficient-deep-learning-for-natural","title":"Knowledge Efficient Deep Learning for Natural Language Processing","date":"2020-08-28","arxiv_id":"2008.12878","n_code_links":0,"syntology":null},{"paper":null,"slug":"tatl-at-w-nut-2020-task-2-a-transformer-based","title":"TATL at W-NUT 2020 Task 2: A Transformer-based Baseline System for Identification of Informative COVID-19 English Tweets","date":"2020-08-28","arxiv_id":"2008.12854","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-conditioned-transformer-for-automatic","title":"Text-Conditioned Transformer for Automatic Pronunciation Error Detection","date":"2020-08-28","arxiv_id":"2008.12424","n_code_links":0,"syntology":null},{"paper":null,"slug":"dave-deriving-automatically-verilog-from","title":"DAVE: Deriving Automatically Verilog from English","date":"2020-08-27","arxiv_id":"2009.01026","n_code_links":0,"syntology":null},{"paper":"/paper/improvement-of-a-dedicated-model-for-open","slug":"improvement-of-a-dedicated-model-for-open","title":"Improvement of a dedicated model for open domain persona-aware dialogue generation","date":"2020-08-27","arxiv_id":"2008.11970","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multitask-deep-learning-approach-for-user","title":"A Multitask Deep Learning Approach for User Depression Detection on Sina Weibo","date":"2020-08-26","arxiv_id":"2008.11708","n_code_links":0,"syntology":null},{"paper":null,"slug":"discrete-word-embedding-for-logical-natural","title":"Discrete Word Embedding for Logical Natural Language Understanding","date":"2020-08-26","arxiv_id":"2008.11649","n_code_links":0,"syntology":null},{"paper":"/paper/etc-nlg-end-to-end-topic-conditioned-natural","slug":"etc-nlg-end-to-end-topic-conditioned-natural","title":"ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation","date":"2020-08-25","arxiv_id":"2008.10875","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamics-of-feed-forward-induced-interference","title":"Dynamics of feed forward induced interference training","date":"2020-08-24","arxiv_id":"2008.11111","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-dialogue-transformer","title":"End to End Dialogue Transformer","date":"2020-08-24","arxiv_id":"2008.10392","n_code_links":0,"syntology":null},{"paper":"/paper/identity-aware-multi-sentence-video","slug":"identity-aware-multi-sentence-video","title":"Identity-Aware Multi-Sentence Video Description","date":"2020-08-22","arxiv_id":"2008.09791","n_code_links":1,"syntology":null},{"paper":"/paper/lite-training-strategies-for-portuguese","slug":"lite-training-strategies-for-portuguese","title":"Lite Training Strategies for Portuguese-English and English-Portuguese Translation","date":"2020-08-20","arxiv_id":"2008.08769","n_code_links":1,"syntology":null},{"paper":"/paper/parade-passage-representation-aggregation-for","slug":"parade-passage-representation-aggregation-for","title":"PARADE: Passage Representation Aggregation for Document Reranking","date":"2020-08-20","arxiv_id":"2008.09093","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["canjiali/PARADE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/ptt5-pretraining-and-validating-the-t5-model","slug":"ptt5-pretraining-and-validating-the-t5-model","title":"PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data","date":"2020-08-20","arxiv_id":"2008.09144","n_code_links":3,"syntology":null},{"paper":"/paper/are-neural-open-domain-dialog-systems-robust","slug":"are-neural-open-domain-dialog-systems-robust","title":"Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study","date":"2020-08-18","arxiv_id":"2008.07683","n_code_links":1,"syntology":null},{"paper":null,"slug":"estimation-of-causal-effects-of-multiple","title":"Estimation of causal effects of multiple treatments in healthcare database studies with rare outcomes","date":"2020-08-18","arxiv_id":"2008.07687","n_code_links":0,"syntology":null},{"paper":"/paper/glancing-transformer-for-non-autoregressive","slug":"glancing-transformer-for-non-autoregressive","title":"Glancing Transformer for Non-Autoregressive Neural Machine Translation","date":"2020-08-18","arxiv_id":"2008.07905","n_code_links":2,"syntology":null},{"paper":"/paper/very-deep-transformers-for-neural-machine","slug":"very-deep-transformers-for-neural-machine","title":"Very Deep Transformers for Neural Machine Translation","date":"2020-08-18","arxiv_id":"2008.07772","n_code_links":4,"syntology":{"ran":8,"of":9,"n_ran_checked":3,"n_instrument":5,"unverified":1,"pointer_only":3,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["namisan/exdeep-nmt"],"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":"generative-models-are-unsupervised-predictors","title":"Generative Models are Unsupervised Predictors of Page Quality: A Colossal-Scale Study","date":"2020-08-17","arxiv_id":"2008.13533","n_code_links":0,"syntology":null},{"paper":null,"slug":"narrative-interpolation-for-generating-and","title":"Narrative Interpolation for Generating and Understanding Stories","date":"2020-08-17","arxiv_id":"2008.07466","n_code_links":0,"syntology":null},{"paper":"/paper/spatial-temporal-transformer-network-for","slug":"spatial-temporal-transformer-network-for","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","date":"2020-08-17","arxiv_id":"2008.07404","n_code_links":1,"syntology":null},{"paper":null,"slug":"adding-recurrence-to-pretrained-transformers","title":"Adding Recurrence to Pretrained Transformers for Improved Efficiency and Context Size","date":"2020-08-16","arxiv_id":"2008.07027","n_code_links":0,"syntology":null},{"paper":null,"slug":"dcr-net-a-deep-co-interactive-relation","title":"DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification","date":"2020-08-16","arxiv_id":"2008.06914","n_code_links":0,"syntology":null},{"paper":null,"slug":"topicbert-a-transformer-transfer-learning","title":"TopicBERT: A Transformer transfer learning based memory-graph approach for multimodal streaming social media topic detection","date":"2020-08-16","arxiv_id":"2008.06877","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-fast-transformers-one-shot-neural","title":"Finding Fast Transformers: One-Shot Neural Architecture Search by Component Composition","date":"2020-08-15","arxiv_id":"2008.06808","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-bert-and-lightgbm-based-model-for","title":"A Hybrid BERT and LightGBM based Model for Predicting Emotion GIF Categories on Twitter","date":"2020-08-14","arxiv_id":"2008.06176","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptable-multi-domain-language-model-for","title":"Adaptable Multi-Domain Language Model for Transformer ASR","date":"2020-08-14","arxiv_id":"2008.06208","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-as-few-shot-learner-for-task","title":"Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems","date":"2020-08-14","arxiv_id":"2008.06239","n_code_links":0,"syntology":null},{"paper":"/paper/a-community-powered-search-of-machine","slug":"a-community-powered-search-of-machine","title":"A community-powered search of machine learning strategy space to find NMR property prediction models","date":"2020-08-13","arxiv_id":"2008.05994","n_code_links":1,"syntology":null},{"paper":null,"slug":"conv-transformer-transducer-low-latency-low","title":"Conv-Transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-End Speech Recognition","date":"2020-08-13","arxiv_id":"2008.05750","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-contextual-perception-and","title":"End-to-end Contextual Perception and Prediction with Interaction Transformer","date":"2020-08-13","arxiv_id":"2008.05927","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-scale-transfer-learning-for-low","title":"Large-scale Transfer Learning for Low-resource Spoken Language Understanding","date":"2020-08-13","arxiv_id":"2008.05671","n_code_links":0,"syntology":null},{"paper":"/paper/mmm-exploring-conditional-multi-track-music","slug":"mmm-exploring-conditional-multi-track-music","title":"MMM : Exploring Conditional Multi-Track Music Generation with the Transformer","date":"2020-08-13","arxiv_id":"2008.06048","n_code_links":3,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"compression-of-deep-learning-models-for-text","title":"Compression of Deep Learning Models for Text: A Survey","date":"2020-08-12","arxiv_id":"2008.05221","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-impact-of-knowledge-graph","slug":"evaluating-the-impact-of-knowledge-graph","title":"Evaluating the Impact of Knowledge Graph Context on Entity Disambiguation Models","date":"2020-08-12","arxiv_id":"2008.05190","n_code_links":1,"syntology":null},{"paper":"/paper/fine-grained-visual-textual-alignment-for","slug":"fine-grained-visual-textual-alignment-for","title":"Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders","date":"2020-08-12","arxiv_id":"2008.05231","n_code_links":1,"syntology":{"ran":14,"of":16,"n_ran_checked":13,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mesnico/TERAN"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/kr-bert-a-small-scale-korean-specific","slug":"kr-bert-a-small-scale-korean-specific","title":"KR-BERT: A Small-Scale Korean-Specific Language Model","date":"2020-08-10","arxiv_id":"2008.03979","n_code_links":1,"syntology":null},{"paper":null,"slug":"navigating-language-models-with-synthetic","title":"Navigating Human Language Models with Synthetic Agents","date":"2020-08-10","arxiv_id":"2008.04162","n_code_links":0,"syntology":null},{"paper":"/paper/pretraining-techniques-for-sequence-to","slug":"pretraining-techniques-for-sequence-to","title":"Pretraining Techniques for Sequence-to-Sequence Voice Conversion","date":"2020-08-07","arxiv_id":"2008.03088","n_code_links":2,"syntology":null},{"paper":"/paper/question-and-answer-test-train-overlap-in","slug":"question-and-answer-test-train-overlap-in","title":"Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets","date":"2020-08-06","arxiv_id":"2008.02637","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: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/QA-Overlap"],"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":"6veclm-language-modeling-in-vector-space-for","title":"6VecLM: Language Modeling in Vector Space for IPv6 Target Generation","date":"2020-08-05","arxiv_id":"2008.02213","n_code_links":0,"syntology":null},{"paper":null,"slug":"select-extract-and-generate-neural-keyphrase","title":"Select, Extract and Generate: Neural Keyphrase Generation with Layer-wise Coverage Attention","date":"2020-08-04","arxiv_id":"2008.01739","n_code_links":0,"syntology":null},{"paper":"/paper/the-jazz-transformer-on-the-front-line","slug":"the-jazz-transformer-on-the-front-line","title":"The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures","date":"2020-08-04","arxiv_id":"2008.01307","n_code_links":2,"syntology":{"ran":13,"of":14,"n_ran_checked":13,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["slSeanWU/MusDr","slSeanWU/jazz_transformer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lt-helsinki-at-semeval-2020-task-12","title":"LT@Helsinki at SemEval-2020 Task 12: Multilingual or language-specific BERT?","date":"2020-08-03","arxiv_id":"2008.00805","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-attention-encoding-and-pooling-for","title":"Self-attention encoding and pooling for speaker recognition","date":"2020-08-03","arxiv_id":"2008.01077","n_code_links":0,"syntology":null},{"paper":"/paper/seqdialn-sequential-visual-dialog-networks-in","slug":"seqdialn-sequential-visual-dialog-networks-in","title":"SeqDialN: Sequential Visual Dialog Networks in Joint Visual-Linguistic Representation Space","date":"2020-08-02","arxiv_id":"2008.00397","n_code_links":1,"syntology":null},{"paper":"/paper/the-chess-transformer-mastering-play-using","slug":"the-chess-transformer-mastering-play-using","title":"The Chess Transformer: Mastering Play using Generative Language Models","date":"2020-08-02","arxiv_id":"2008.04057","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"multi-node-bert-pretraining-cost-efficient","title":"Multi-node Bert-pretraining: Cost-efficient Approach","date":"2020-08-01","arxiv_id":"2008.00177","n_code_links":0,"syntology":null},{"paper":"/paper/trojaning-language-models-for-fun-and-profit","slug":"trojaning-language-models-for-fun-and-profit","title":"Trojaning Language Models for Fun and Profit","date":"2020-08-01","arxiv_id":"2008.00312","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-learning-universal-representations-across","title":"On Learning Universal Representations Across Languages","date":"2020-07-31","arxiv_id":"2007.15960","n_code_links":0,"syntology":null},{"paper":"/paper/tweepfake-about-detecting-deepfake-tweets","slug":"tweepfake-about-detecting-deepfake-tweets","title":"TweepFake: about Detecting Deepfake Tweets","date":"2020-07-31","arxiv_id":"2008.00036","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-multi-view-spatiotemporal-virtual-graph","title":"Deep Multi-View Spatiotemporal Virtual Graph Neural Network for Significant Citywide Ride-hailing Demand Prediction","date":"2020-07-30","arxiv_id":"2007.15189","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-contextual-team-aware-item","slug":"interpretable-contextual-team-aware-item","title":"Interpretable Contextual Team-aware Item Recommendation: Application in Multiplayer Online Battle Arena Games","date":"2020-07-30","arxiv_id":"2007.15236","n_code_links":1,"syntology":null},{"paper":"/paper/composer-style-classification-of-piano-sheet","slug":"composer-style-classification-of-piano-sheet","title":"Composer Style Classification of Piano Sheet Music Images Using Language Model Pretraining","date":"2020-07-29","arxiv_id":"2007.14587","n_code_links":1,"syntology":null},{"paper":null,"slug":"tensorcoder-dimension-wise-attention-via","title":"TensorCoder: Dimension-Wise Attention via Tensor Representation for Natural Language Modeling","date":"2020-07-28","arxiv_id":"2008.01547","n_code_links":0,"syntology":null},{"paper":null,"slug":"to-bert-or-not-to-bert-comparing-speech-and","title":"To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection","date":"2020-07-26","arxiv_id":"2008.01551","n_code_links":0,"syntology":null},{"paper":"/paper/fissa-at-semeval-2020-task-9-fine-tuned-for","slug":"fissa-at-semeval-2020-task-9-fine-tuned-for","title":"FiSSA at SemEval-2020 Task 9: Fine-tuned For Feelings","date":"2020-07-24","arxiv_id":"2007.12544","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-swedish-english-fasttext-embeddings","slug":"exploring-swedish-english-fasttext-embeddings","title":"Exploring Swedish & English fastText Embeddings for NER with the Transformer","date":"2020-07-23","arxiv_id":"2007.16007","n_code_links":1,"syntology":null},{"paper":null,"slug":"analogical-reasoning-for-visually-grounded","title":"Analogical Reasoning for Visually Grounded Language Acquisition","date":"2020-07-22","arxiv_id":"2007.11668","n_code_links":0,"syntology":null},{"paper":"/paper/crosstransformers-spatially-aware-few-shot","slug":"crosstransformers-spatially-aware-few-shot","title":"CrossTransformers: spatially-aware few-shot transfer","date":"2020-07-22","arxiv_id":"2007.11498","n_code_links":6,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/meta-dataset"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed"]}}},{"paper":"/paper/neural-machine-translation-with-error","slug":"neural-machine-translation-with-error","title":"Neural Machine Translation with Error Correction","date":"2020-07-21","arxiv_id":"2007.10681","n_code_links":1,"syntology":null},{"paper":null,"slug":"sliceout-training-transformers-and-cnns","title":"Improving compute efficacy frontiers with SliceOut","date":"2020-07-21","arxiv_id":"2007.10909","n_code_links":0,"syntology":null},{"paper":"/paper/conformer-kernel-with-query-term-independence","slug":"conformer-kernel-with-query-term-independence","title":"Conformer-Kernel with Query Term Independence for Document Retrieval","date":"2020-07-20","arxiv_id":"2007.10434","n_code_links":1,"syntology":null},{"paper":"/paper/learning-joint-spatial-temporal","slug":"learning-joint-spatial-temporal","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","date":"2020-07-20","arxiv_id":"2007.10247","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":2,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["researchmm/STTN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"feature-pyramid-transformer","title":"Feature Pyramid Transformer","date":"2020-07-18","arxiv_id":"2007.09451","n_code_links":0,"syntology":null},{"paper":"/paper/temporal-pointwise-convolutional-networks-for","slug":"temporal-pointwise-convolutional-networks-for","title":"Temporal Pointwise Convolutional Networks for Length of Stay Prediction in the Intensive Care Unit","date":"2020-07-18","arxiv_id":"2007.09483","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-based-traffic-surveillance","title":"Deep Learning Based Traffic Surveillance System For Missing and Suspicious Car Detection","date":"2020-07-17","arxiv_id":"2007.08783","n_code_links":0,"syntology":null},{"paper":"/paper/generative-pretraining-from-pixels","slug":"generative-pretraining-from-pixels","title":"Generative Pretraining from Pixels","date":"2020-07-17","arxiv_id":null,"n_code_links":4,"syntology":null},{"paper":"/paper/hopfield-networks-is-all-you-need","slug":"hopfield-networks-is-all-you-need","title":"Hopfield Networks is All You Need","date":"2020-07-16","arxiv_id":"2008.02217","n_code_links":3,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ml-jku/hopfield-layers"],"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/investigating-pretrained-language-models-for","slug":"investigating-pretrained-language-models-for","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","date":"2020-07-16","arxiv_id":"2007.08426","n_code_links":3,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["UKPLab/plms-graph2text"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/infoxlm-an-information-theoretic-framework","slug":"infoxlm-an-information-theoretic-framework","title":"InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training","date":"2020-07-15","arxiv_id":"2007.07834","n_code_links":4,"syntology":null},{"paper":null,"slug":"the-monte-carlo-transformer-a-stochastic-self","title":"The Monte Carlo Transformer: a stochastic self-attention model for sequence prediction","date":"2020-07-15","arxiv_id":"2007.08620","n_code_links":0,"syntology":null},{"paper":"/paper/contextualized-code-representation-learning","slug":"contextualized-code-representation-learning","title":"CoreGen: Contextualized Code Representation Learning for Commit Message Generation","date":"2020-07-14","arxiv_id":"2007.06934","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-transformer-based-data-augmentation-with","title":"Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR","date":"2020-07-14","arxiv_id":"2007.06949","n_code_links":0,"syntology":null},{"paper":"/paper/emoji-prediction-extensions-and-benchmarking","slug":"emoji-prediction-extensions-and-benchmarking","title":"Emoji Prediction: Extensions and Benchmarking","date":"2020-07-14","arxiv_id":"2007.07389","n_code_links":1,"syntology":null},{"paper":"/paper/paranoid-transformer-reading-narrative-of","slug":"paranoid-transformer-reading-narrative-of","title":"Paranoid Transformer: Reading Narrative of Madness as Computational Approach to Creativity","date":"2020-07-13","arxiv_id":"2007.06290","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-with-depth-wise-lstm","title":"Rewiring the Transformer with Depth-Wise LSTMs","date":"2020-07-13","arxiv_id":"2007.06257","n_code_links":0,"syntology":null},{"paper":null,"slug":"hypergrid-efficient-multi-task-transformers","title":"HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections","date":"2020-07-12","arxiv_id":"2007.05891","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-graph-to-sequence-learning-for-vision","title":"Sparse Graph to Sequence Learning for Vision Conditioned Long Textual Sequence Generation","date":"2020-07-12","arxiv_id":"2007.06077","n_code_links":0,"syntology":null},{"paper":"/paper/tera-self-supervised-learning-of-transformer","slug":"tera-self-supervised-learning-of-transformer","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","date":"2020-07-12","arxiv_id":"2007.06028","n_code_links":7,"syntology":{"ran":11,"of":14,"n_ran_checked":7,"n_instrument":4,"unverified":3,"pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning","s3prl/s3prl"],"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/sequence-generation-with-mixed","slug":"sequence-generation-with-mixed","title":"Sequence Generation with Mixed Representations","date":"2020-07-11","arxiv_id":null,"n_code_links":1,"syntology":null}],"record_sha256":"ae533eb4ff5dca432849ddd230eb200245088cb1fc191b195ba688435d6c3bd5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}