{"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/176","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":176,"pages_in_order":190,"rows_per_page":100,"rows":[17501,17600],"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/175","next":"/method/bpe/papers/177","papers":[{"paper":"/paper/interlocking-backpropagation-improving","slug":"interlocking-backpropagation-improving","title":"Interlocking Backpropagation: Improving depthwise model-parallelism","date":"2020-10-08","arxiv_id":"2010.04116","n_code_links":1,"syntology":null},{"paper":"/paper/shallow-to-deep-training-for-neural-machine","slug":"shallow-to-deep-training-for-neural-machine","title":"Shallow-to-Deep Training for Neural Machine Translation","date":"2020-10-08","arxiv_id":"2010.03737","n_code_links":1,"syntology":null},{"paper":"/paper/textsettr-label-free-text-style-extraction-1","slug":"textsettr-label-free-text-style-extraction-1","title":"TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling","date":"2020-10-08","arxiv_id":"2010.03802","n_code_links":1,"syntology":null},{"paper":"/paper/visualnews-a-large-multi-source-news-image","slug":"visualnews-a-large-multi-source-news-image","title":"Visual News: Benchmark and Challenges in News Image Captioning","date":"2020-10-08","arxiv_id":"2010.03743","n_code_links":1,"syntology":null},{"paper":"/paper/low-resource-domain-adaptation-for","slug":"low-resource-domain-adaptation-for","title":"Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing","date":"2020-10-07","arxiv_id":"2010.03546","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-transformers-with-approximate-1","slug":"optimizing-transformers-with-approximate-1","title":"AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models","date":"2020-10-07","arxiv_id":"2010.03688","n_code_links":1,"syntology":null},{"paper":"/paper/super-human-performance-in-online-low-latency","slug":"super-human-performance-in-online-low-latency","title":"Super-Human Performance in Online Low-latency Recognition of Conversational Speech","date":"2020-10-07","arxiv_id":"2010.03449","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-gcrf-recovering-chinese-dropped","slug":"transformer-gcrf-recovering-chinese-dropped","title":"Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields","date":"2020-10-07","arxiv_id":"2010.03224","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-grammatical-error-correction","title":"Adversarial Grammatical Error Correction","date":"2020-10-06","arxiv_id":"2010.02407","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-tokenization-strategies","slug":"an-empirical-study-of-tokenization-strategies","title":"An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks","date":"2020-10-06","arxiv_id":"2010.02534","n_code_links":1,"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":["kakaobrain/kortok"],"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":"/paper/analyzing-individual-neurons-in-pre-trained","slug":"analyzing-individual-neurons-in-pre-trained","title":"Analyzing Individual Neurons in Pre-trained Language Models","date":"2020-10-06","arxiv_id":"2010.02695","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-cls-through-ranking-by-generation","title":"Beyond [CLS] through Ranking by Generation","date":"2020-10-06","arxiv_id":"2010.03073","n_code_links":0,"syntology":null},{"paper":"/paper/converting-the-point-of-view-of-messages","slug":"converting-the-point-of-view-of-messages","title":"Converting the Point of View of Messages Spoken to Virtual Assistants","date":"2020-10-06","arxiv_id":"2010.02600","n_code_links":2,"syntology":null},{"paper":null,"slug":"efficient-inference-for-neural-machine","title":"Efficient Inference For Neural Machine Translation","date":"2020-10-06","arxiv_id":"2010.02416","n_code_links":0,"syntology":null},{"paper":null,"slug":"incorporating-behavioral-hypotheses-for-query","title":"Incorporating Behavioral Hypotheses for Query Generation","date":"2020-10-06","arxiv_id":"2010.02667","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-african-american-vernacular","slug":"investigating-african-american-vernacular","title":"Investigating African-American Vernacular English in Transformer-Based Text Generation","date":"2020-10-06","arxiv_id":"2010.02510","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-sub-layer-functionalities-of","title":"On the Sub-Layer Functionalities of Transformer Decoder","date":"2020-10-06","arxiv_id":"2010.02648","n_code_links":0,"syntology":null},{"paper":null,"slug":"resource-enhanced-neural-model-for-event","title":"Resource-Enhanced Neural Model for Event Argument Extraction","date":"2020-10-06","arxiv_id":"2010.03022","n_code_links":0,"syntology":null},{"paper":null,"slug":"vector-vector-matrix-architecture-a-novel","title":"Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in NLP Applications","date":"2020-10-06","arxiv_id":"2010.08412","n_code_links":0,"syntology":null},{"paper":"/paper/genaug-data-augmentation-for-finetuning-text","slug":"genaug-data-augmentation-for-finetuning-text","title":"GenAug: Data Augmentation for Finetuning Text Generators","date":"2020-10-05","arxiv_id":"2010.01794","n_code_links":2,"syntology":null},{"paper":null,"slug":"how-effective-is-task-agnostic-data","title":"How Effective is Task-Agnostic Data Augmentation for Pretrained Transformers?","date":"2020-10-05","arxiv_id":"2010.01764","n_code_links":0,"syntology":null},{"paper":null,"slug":"pair-planning-and-iterative-refinement-in-pre","title":"PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation","date":"2020-10-05","arxiv_id":"2010.02301","n_code_links":0,"syntology":null},{"paper":"/paper/pruning-redundant-mappings-in-transformer","slug":"pruning-redundant-mappings-in-transformer","title":"Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior","date":"2020-10-05","arxiv_id":"2010.01791","n_code_links":1,"syntology":null},{"paper":null,"slug":"pum-at-semeval-2020-task-12-aggregation-of","title":"PUM at SemEval-2020 Task 12: Aggregation of Transformer-based models' features for offensive language recognition","date":"2020-10-05","arxiv_id":"2010.01897","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-neural-text-generation-with","slug":"transformer-based-neural-text-generation-with","title":"Transformer-Based Neural Text Generation with Syntactic Guidance","date":"2020-10-05","arxiv_id":"2010.01737","n_code_links":1,"syntology":null},{"paper":"/paper/inquisitive-question-generation-for-high","slug":"inquisitive-question-generation-for-high","title":"Inquisitive Question Generation for High Level Text Comprehension","date":"2020-10-04","arxiv_id":"2010.01657","n_code_links":1,"syntology":null},{"paper":"/paper/tell-me-how-to-ask-again-question-data","slug":"tell-me-how-to-ask-again-question-data","title":"Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space","date":"2020-10-04","arxiv_id":"2010.01475","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-chemical-1d-knowledge-using","title":"Beyond Chemical 1D knowledge using Transformers","date":"2020-10-02","arxiv_id":"2010.01027","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-transfer-approaches-to-improve-seq-to","title":"Data Transfer Approaches to Improve Seq-to-Seq Retrosynthesis","date":"2020-10-02","arxiv_id":"2010.00792","n_code_links":0,"syntology":null},{"paper":"/paper/stil-simultaneous-slot-filling-translation","slug":"stil-simultaneous-slot-filling-translation","title":"STIL -- Simultaneous Slot Filling, Translation, Intent Classification, and Language Identification: Initial Results using mBART on MultiATIS++","date":"2020-10-02","arxiv_id":"2010.00760","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-compare-aggregate-transformer-for","title":"A Compare Aggregate Transformer for Understanding Document-grounded Dialogue","date":"2020-10-01","arxiv_id":"2010.00190","n_code_links":0,"syntology":null},{"paper":"/paper/colake-contextualized-language-and-knowledge","slug":"colake-contextualized-language-and-knowledge","title":"CoLAKE: Contextualized Language and Knowledge Embedding","date":"2020-10-01","arxiv_id":"2010.00309","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["txsun1997/CoLAKE"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-multilingual-bert-for-estonian","title":"Evaluating Multilingual BERT for Estonian","date":"2020-10-01","arxiv_id":"2010.00454","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-the-rhetorical-capacities-of-neural","title":"Examining the rhetorical capacities of neural language models","date":"2020-10-01","arxiv_id":"2010.00153","n_code_links":0,"syntology":null},{"paper":"/paper/phonemer-at-wnut-2020-task-2-sequence","slug":"phonemer-at-wnut-2020-task-2-sequence","title":"Phonemer at WNUT-2020 Task 2: Sequence Classification Using COVID Twitter BERT and Bagging Ensemble Technique based on Plurality Voting","date":"2020-10-01","arxiv_id":"2010.00294","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-state-of-the-art-natural-1","slug":"transformers-state-of-the-art-natural-1","title":"Transformers: State-of-the-Art Natural Language Processing","date":"2020-10-01","arxiv_id":null,"n_code_links":3,"syntology":null},{"paper":null,"slug":"wechat-neural-machine-translation-systems-for","title":"WeChat Neural Machine Translation Systems for WMT20","date":"2020-10-01","arxiv_id":"2010.00247","n_code_links":0,"syntology":null},{"paper":"/paper/a-vietnamese-dataset-for-evaluating-machine","slug":"a-vietnamese-dataset-for-evaluating-machine","title":"A Vietnamese Dataset for Evaluating Machine Reading Comprehension","date":"2020-09-30","arxiv_id":"2009.14725","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-hard-retrieval-cross-attention-for","title":"Learning Hard Retrieval Decoder Attention for Transformers","date":"2020-09-30","arxiv_id":"2009.14658","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-systematic-generalization-in-neural","slug":"measuring-systematic-generalization-in-neural","title":"Measuring Systematic Generalization in Neural Proof Generation with Transformers","date":"2020-09-30","arxiv_id":"2009.14786","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["NicolasAG/SGinPG"],"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":["official"]}}},{"paper":null,"slug":"mqtransformer-multi-horizon-forecasts-with","title":"MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention","date":"2020-09-30","arxiv_id":"2009.14799","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-attention-with-performers","slug":"rethinking-attention-with-performers","title":"Rethinking Attention with Performers","date":"2020-09-30","arxiv_id":"2009.14794","n_code_links":7,"syntology":{"ran":11,"of":16,"n_ran_checked":7,"n_instrument":4,"unverified":5,"pointer_only":6,"phrase":"11 ran (of which 3 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) · 5 unverified","official":{"repos":["google-research/google-research"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/a-simple-but-tough-to-beat-data-augmentation","slug":"a-simple-but-tough-to-beat-data-augmentation","title":"A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation","date":"2020-09-29","arxiv_id":"2009.13818","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["dinghanshen/Cutoff"],"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":["official"]}}},{"paper":null,"slug":"attention-that-does-not-explain-away","title":"Attention that does not Explain Away","date":"2020-09-29","arxiv_id":"2009.14308","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-prediction-using-limited-twitter-data","title":"Gender prediction using limited Twitter Data","date":"2020-09-29","arxiv_id":"2010.02005","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-learning-for-indonesian","slug":"sequence-to-sequence-learning-for-indonesian","title":"Sequence-to-Sequence Learning for Indonesian Automatic Question Generator","date":"2020-09-29","arxiv_id":"2009.13889","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-design-and-implementation-of-language","title":"The design and implementation of Language Learning Chatbot with XAI using Ontology and Transfer Learning","date":"2020-09-29","arxiv_id":"2009.13984","n_code_links":0,"syntology":null},{"paper":"/paper/visually-grounded-planning-without-vision","slug":"visually-grounded-planning-without-vision","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","date":"2020-09-29","arxiv_id":"2009.14259","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":["cognitiveailab/alfred-gpt2"],"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":"accelerating-multi-model-inference-by-merging","title":"Accelerating Multi-Model Inference by Merging DNNs of Different Weights","date":"2020-09-28","arxiv_id":"2009.13062","n_code_links":0,"syntology":null},{"paper":"/paper/deep-transformers-with-latent-depth","slug":"deep-transformers-with-latent-depth","title":"Deep Transformers with Latent Depth","date":"2020-09-28","arxiv_id":"2009.13102","n_code_links":1,"syntology":null},{"paper":"/paper/vivo-surpassing-human-performance-in-novel","slug":"vivo-surpassing-human-performance-in-novel","title":"VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning","date":"2020-09-28","arxiv_id":"2009.13682","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-does-it-mean-to-be-language-agnostic","title":"What does it mean to be language-agnostic? Probing multilingual sentence encoders for typological properties","date":"2020-09-27","arxiv_id":"2009.12862","n_code_links":0,"syntology":null},{"paper":"/paper/kg-bart-knowledge-graph-augmented-bart-for","slug":"kg-bart-knowledge-graph-augmented-bart-for","title":"KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning","date":"2020-09-26","arxiv_id":"2009.12677","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yeliu918/KG-BART"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-little-goes-a-long-way-improving-toxic","slug":"a-little-goes-a-long-way-improving-toxic","title":"A little goes a long way: Improving toxic language classification despite data scarcity","date":"2020-09-25","arxiv_id":"2009.12344","n_code_links":1,"syntology":null},{"paper":"/paper/bet-a-backtranslation-approach-for-easy-data","slug":"bet-a-backtranslation-approach-for-easy-data","title":"BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification Context","date":"2020-09-25","arxiv_id":"2009.12452","n_code_links":1,"syntology":null},{"paper":"/paper/mintl-minimalist-transfer-learning-for-task","slug":"mintl-minimalist-transfer-learning-for-task","title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","date":"2020-09-25","arxiv_id":"2009.12005","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zlinao/MinTL"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"weird-ai-yankovic-generating-parody-lyrics","title":"Weird AI Yankovic: Generating Parody Lyrics","date":"2020-09-25","arxiv_id":"2009.12240","n_code_links":0,"syntology":null},{"paper":"/paper/toward-a-thermodynamics-of-meaning","slug":"toward-a-thermodynamics-of-meaning","title":"Toward a Thermodynamics of Meaning","date":"2020-09-24","arxiv_id":"2009.11963","n_code_links":1,"syntology":null},{"paper":null,"slug":"hamming-ocr-a-locality-sensitive-hashing","title":"Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition","date":"2020-09-23","arxiv_id":"2009.10874","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-pass-transformer-for-machine","title":"Multi-Pass Transformer for Machine Translation","date":"2020-09-23","arxiv_id":"2009.11382","n_code_links":0,"syntology":null},{"paper":null,"slug":"robustification-of-segmentation-models","title":"Robustification of Segmentation Models Against Adversarial Perturbations In Medical Imaging","date":"2020-09-23","arxiv_id":"2009.11090","n_code_links":0,"syntology":null},{"paper":"/paper/seq2edits-sequence-transduction-using-span","slug":"seq2edits-sequence-transduction-using-span","title":"Seq2Edits: Sequence Transduction Using Span-level Edit Operations","date":"2020-09-23","arxiv_id":"2009.11136","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-data-augmentation-for-extreme-multi-label","title":"On Data Augmentation for Extreme Multi-label Classification","date":"2020-09-22","arxiv_id":"2009.10778","n_code_links":0,"syntology":null},{"paper":"/paper/alleviating-the-inequality-of-attention-heads","slug":"alleviating-the-inequality-of-attention-heads","title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","date":"2020-09-21","arxiv_id":"2009.09672","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-acoustic-events-using-convolutional","title":"Detecting Sound Events Using Convolutional Macaron Net With Pseudo Strong Labels","date":"2020-09-21","arxiv_id":"2009.09632","n_code_links":0,"syntology":null},{"paper":"/paper/empathetic-dialogue-generation-via-knowledge","slug":"empathetic-dialogue-generation-via-knowledge","title":"Knowledge Bridging for Empathetic Dialogue Generation","date":"2020-09-21","arxiv_id":"2009.09708","n_code_links":1,"syntology":null},{"paper":"/paper/ucd-cs-at-w-nut-2020-shared-task-3-a-text-to","slug":"ucd-cs-at-w-nut-2020-shared-task-3-a-text-to","title":"UCD-CS at W-NUT 2020 Shared Task-3: A Text to Text Approach for COVID-19 Event Extraction on Social Media","date":"2020-09-21","arxiv_id":"2009.10047","n_code_links":1,"syntology":null},{"paper":"/paper/conditionally-adaptive-multi-task-learning","slug":"conditionally-adaptive-multi-task-learning","title":"Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data","date":"2020-09-19","arxiv_id":"2009.09139","n_code_links":1,"syntology":null},{"paper":null,"slug":"prior-art-search-and-reranking-for-generated","title":"Prior Art Search and Reranking for Generated Patent Text","date":"2020-09-19","arxiv_id":"2009.09132","n_code_links":0,"syntology":null},{"paper":"/paper/towards-computational-linguistics-in","slug":"towards-computational-linguistics-in","title":"Towards Computational Linguistics in Minangkabau Language: Studies on Sentiment Analysis and Machine Translation","date":"2020-09-19","arxiv_id":"2009.09309","n_code_links":1,"syntology":null},{"paper":null,"slug":"hardware-accelerator-for-multi-head-attention","title":"Hardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer","date":"2020-09-18","arxiv_id":"2009.08605","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-gpt-with-congruent-transformers","title":"Hierarchical GPT with Congruent Transformers for Multi-Sentence Language Models","date":"2020-09-18","arxiv_id":"2009.08636","n_code_links":0,"syntology":null},{"paper":"/paper/distilled-one-shot-federated-learning","slug":"distilled-one-shot-federated-learning","title":"Distilled One-Shot Federated Learning","date":"2020-09-17","arxiv_id":"2009.07999","n_code_links":1,"syntology":null},{"paper":"/paper/graphcodebert-pre-training-code","slug":"graphcodebert-pre-training-code","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","date":"2020-09-17","arxiv_id":"2009.08366","n_code_links":1,"syntology":null},{"paper":"/paper/multi-2oie-multilingual-open-information","slug":"multi-2oie-multilingual-open-information","title":"Multi$^2$OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT","date":"2020-09-17","arxiv_id":"2009.08128","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":2,"n_instrument":4,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["youngbin-ro/Multi2OIE"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-fully-8-bit-integer-inference-for-the","title":"Towards Fully 8-bit Integer Inference for the Transformer Model","date":"2020-09-17","arxiv_id":"2009.08034","n_code_links":0,"syntology":null},{"paper":"/paper/automated-source-code-generation-and-auto","slug":"automated-source-code-generation-and-auto","title":"Automated Source Code Generation and Auto-completion Using Deep Learning: Comparing and Discussing Current Language-Model-Related Approaches","date":"2020-09-16","arxiv_id":"2009.07740","n_code_links":1,"syntology":null},{"paper":"/paper/cogtree-cognition-tree-loss-for-unbiased","slug":"cogtree-cognition-tree-loss-for-unbiased","title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","date":"2020-09-16","arxiv_id":"2009.07526","n_code_links":1,"syntology":null},{"paper":null,"slug":"document-level-neural-machine-translation-1","title":"Document-level Neural Machine Translation with Document Embeddings","date":"2020-09-16","arxiv_id":"2009.08775","n_code_links":0,"syntology":null},{"paper":null,"slug":"extremely-low-bit-transformer-quantization","title":"Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation","date":"2020-09-16","arxiv_id":"2009.07453","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-to-sequence-neural-machine-translation","title":"Graph-to-Sequence Neural Machine Translation","date":"2020-09-16","arxiv_id":"2009.07489","n_code_links":0,"syntology":null},{"paper":null,"slug":"nabu-multilingual-graph-based-neural-rdf","title":"NABU $\\mathrm{-}$ Multilingual Graph-based Neural RDF Verbalizer","date":"2020-09-16","arxiv_id":"2009.07728","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrofitting-structure-aware-transformer","title":"Retrofitting Structure-aware Transformer Language Model for End Tasks","date":"2020-09-16","arxiv_id":"2009.07408","n_code_links":0,"syntology":null},{"paper":"/paper/attention-aware-inference-for-neural","slug":"attention-aware-inference-for-neural","title":"Global-aware Beam Search for Neural Abstractive Summarization","date":"2020-09-15","arxiv_id":"2009.06891","n_code_links":2,"syntology":null},{"paper":"/paper/critical-thinking-for-language-models","slug":"critical-thinking-for-language-models","title":"Critical Thinking for Language Models","date":"2020-09-15","arxiv_id":"2009.07185","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["debatelab/aacorpus"],"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":"/paper/dialogue-response-ranking-training-with-large","slug":"dialogue-response-ranking-training-with-large","title":"Dialogue Response Ranking Training with Large-Scale Human Feedback Data","date":"2020-09-15","arxiv_id":"2009.06978","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"event-presence-prediction-helps-trigger","title":"Event Presence Prediction Helps Trigger Detection Across Languages","date":"2020-09-15","arxiv_id":"2009.07188","n_code_links":0,"syntology":null},{"paper":"/paper/it-s-not-just-size-that-matters-small","slug":"it-s-not-just-size-that-matters-small","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","date":"2020-09-15","arxiv_id":"2009.07118","n_code_links":5,"syntology":null},{"paper":null,"slug":"the-radicalization-risks-of-gpt-3-and","title":"The Radicalization Risks of GPT-3 and Advanced Neural Language Models","date":"2020-09-15","arxiv_id":"2009.06807","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-transformers-a-survey","title":"Efficient Transformers: A Survey","date":"2020-09-14","arxiv_id":"2009.06732","n_code_links":0,"syntology":null},{"paper":"/paper/gedi-generative-discriminator-guided-sequence","slug":"gedi-generative-discriminator-guided-sequence","title":"GeDi: Generative Discriminator Guided Sequence Generation","date":"2020-09-14","arxiv_id":"2009.06367","n_code_links":3,"syntology":{"ran":6,"of":11,"n_ran_checked":3,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["salesforce/GeDi"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"boostingbert-integrating-multi-class-boosting","title":"BoostingBERT:Integrating Multi-Class Boosting into BERT for NLP Tasks","date":"2020-09-13","arxiv_id":"2009.05959","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-pre-trained-contextual-embeddings","title":"Fine-tuning Pre-trained Contextual Embeddings for Citation Content Analysis in Scholarly Publication","date":"2020-09-12","arxiv_id":"2009.05836","n_code_links":0,"syntology":null},{"paper":"/paper/compressed-deep-networks-goodbye-svd-hello","slug":"compressed-deep-networks-goodbye-svd-hello","title":"Compressed Deep Networks: Goodbye SVD, Hello Robust Low-Rank Approximation","date":"2020-09-11","arxiv_id":"2009.05647","n_code_links":1,"syntology":null},{"paper":"/paper/gtea-representation-learning-for-temporal","slug":"gtea-representation-learning-for-temporal","title":"GTEA: Inductive Representation Learning on Temporal Interaction Graphs via Temporal Edge Aggregation","date":"2020-09-11","arxiv_id":"2009.05266","n_code_links":2,"syntology":null},{"paper":"/paper/unit-test-case-generation-with-transformers","slug":"unit-test-case-generation-with-transformers","title":"Unit Test Case Generation with Transformers and Focal Context","date":"2020-09-11","arxiv_id":"2009.05617","n_code_links":1,"syntology":null},{"paper":"/paper/upb-at-semeval-2020-task-6-pretrained","slug":"upb-at-semeval-2020-task-6-pretrained","title":"UPB at SemEval-2020 Task 6: Pretrained Language Models for Definition Extraction","date":"2020-09-11","arxiv_id":"2009.05603","n_code_links":3,"syntology":null},{"paper":"/paper/brain2word-decoding-brain-activity-for","slug":"brain2word-decoding-brain-activity-for","title":"Brain2Word: Decoding Brain Activity for Language Generation","date":"2020-09-10","arxiv_id":"2009.04765","n_code_links":1,"syntology":null},{"paper":"/paper/filter-an-enhanced-fusion-method-for-cross","slug":"filter-an-enhanced-fusion-method-for-cross","title":"FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding","date":"2020-09-10","arxiv_id":"2009.05166","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"learning-universal-representations-from-word","title":"Learning Universal Representations from Word to Sentence","date":"2020-09-10","arxiv_id":"2009.04656","n_code_links":0,"syntology":null}],"record_sha256":"b3750e9cca91de61fc8a13762950f878aadc0b96d64af77c404db585ad251c90","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}