{"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/128","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":128,"pages_in_order":140,"rows_per_page":100,"rows":[12701,12800],"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/127","next":"/method/absolute-position-encodings/papers/129","papers":[{"paper":"/paper/a-co-interactive-transformer-for-joint-slot","slug":"a-co-interactive-transformer-for-joint-slot","title":"A Co-Interactive Transformer for Joint Slot Filling and Intent Detection","date":"2020-10-08","arxiv_id":"2010.03880","n_code_links":1,"syntology":null},{"paper":"/paper/deformable-detr-deformable-transformers-for-1","slug":"deformable-detr-deformable-transformers-for-1","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","date":"2020-10-08","arxiv_id":"2010.04159","n_code_links":20,"syntology":{"ran":37,"of":55,"n_ran_checked":24,"n_instrument":13,"unverified":18,"pointer_only":21,"phrase":"37 ran (of which 9 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 3 violated, 20 with no contract checked; 13 where Syntology's instrument failed) · 18 unverified","official":{"repos":["fundamentalvision/Deformable-DETR"],"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":"improving-attention-mechanism-with-query","title":"Improving Attention Mechanism with Query-Value Interaction","date":"2020-10-08","arxiv_id":"2010.03766","n_code_links":0,"syntology":null},{"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/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/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":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":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/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/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":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":"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":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":"/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/improve-transformer-models-with-better","slug":"improve-transformer-models-with-better","title":"Improve Transformer Models with Better Relative Position Embeddings","date":"2020-09-28","arxiv_id":"2009.13658","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":"/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":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":"/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":"/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/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":"/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":"/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":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":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":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":"/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":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},{"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":"/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":"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":"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/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":"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":"/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":"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/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":"/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":"/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":"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":"/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/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":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}],"record_sha256":"c1a62764b4c4593af4016fd8dedea91fd24c32fc5f0a2be5ea1f6cecca90a45d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}