{"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/138","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":138,"pages_in_order":140,"rows_per_page":100,"rows":[13701,13800],"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/137","next":"/method/absolute-position-encodings/papers/139","papers":[{"paper":"/paper/190600138","slug":"190600138","title":"Efficient Adaptation of Pretrained Transformers for Abstractive Summarization","date":"2019-06-01","arxiv_id":"1906.00138","n_code_links":2,"syntology":null},{"paper":"/paper/190600295","slug":"190600295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","date":"2019-06-01","arxiv_id":"1906.00295","n_code_links":4,"syntology":{"ran":8,"of":17,"n_ran_checked":5,"n_instrument":3,"unverified":9,"pointer_only":10,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","official":{"repos":["yaohungt/Multimodal-Transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"blcu_nlp-at-semeval-2019-task-8-a-contextual","title":"BLCU\\_NLP at SemEval-2019 Task 8: A Contextual Knowledge-enhanced GPT Model for Fact Checking","date":"2019-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-cuneiform-language-identification","title":"Improving Cuneiform Language Identification with BERT","date":"2019-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/laf-net-locally-adaptive-fusion-networks-for","slug":"laf-net-locally-adaptive-fusion-networks-for","title":"LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation","date":"2019-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/learning-roi-transformer-for-oriented-object","slug":"learning-roi-transformer-for-oriented-object","title":"Learning RoI Transformer for Oriented Object Detection in Aerial Images","date":"2019-06-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"neural-machine-translation-between-myanmar","title":"Neural Machine Translation between Myanmar (Burmese) and Rakhine (Arakanese)","date":"2019-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nuli-at-semeval-2019-task-6-transfer-learning","title":"NULI at SemEval-2019 Task 6: Transfer Learning for Offensive Language Detection using Bidirectional Transformers","date":"2019-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/sequence-modeling-of-temporal-credit","slug":"sequence-modeling-of-temporal-credit","title":"Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement Learning","date":"2019-05-31","arxiv_id":"1905.13420","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/hierarchical-transformers-for-multi-document","slug":"hierarchical-transformers-for-multi-document","title":"Hierarchical Transformers for Multi-Document Summarization","date":"2019-05-30","arxiv_id":"1905.13164","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nlpyang/hiersumm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/path-augmented-graph-transformer-network","slug":"path-augmented-graph-transformer-network","title":"Path-Augmented Graph Transformer Network","date":"2019-05-29","arxiv_id":"1905.12712","n_code_links":2,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["benatorc/PA-Graph-Transformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/interpreting-and-improving-natural-language","slug":"interpreting-and-improving-natural-language","title":"Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)","date":"2019-05-28","arxiv_id":"1905.11833","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["mtoneva/brain_language_nlp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/levenshtein-transformer","slug":"levenshtein-transformer","title":"Levenshtein Transformer","date":"2019-05-27","arxiv_id":"1905.11006","n_code_links":3,"syntology":null},{"paper":"/paper/stochastic-shared-embeddings-data-driven","slug":"stochastic-shared-embeddings-data-driven","title":"Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers","date":"2019-05-25","arxiv_id":"1905.10630","n_code_links":3,"syntology":null},{"paper":null,"slug":"a-call-for-prudent-choice-of-subword-merge","title":"A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translation","date":"2019-05-24","arxiv_id":"1905.10453","n_code_links":0,"syntology":null},{"paper":null,"slug":"scram-spatially-coherent-randomized-attention","title":"SCRAM: Spatially Coherent Randomized Attention Maps","date":"2019-05-24","arxiv_id":"1905.10308","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-multi-head-self-attention","slug":"analyzing-multi-head-self-attention","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","date":"2019-05-23","arxiv_id":"1905.09418","n_code_links":1,"syntology":null},{"paper":"/paper/fastspeech-fast-robust-and-controllable-text","slug":"fastspeech-fast-robust-and-controllable-text","title":"FastSpeech: Fast, Robust and Controllable Text to Speech","date":"2019-05-22","arxiv_id":"1905.09263","n_code_links":22,"syntology":{"ran":10,"of":11,"n_ran_checked":7,"n_instrument":3,"unverified":1,"pointer_only":3,"phrase":"10 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; 3 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/fastspeech-fastrobustand-controllable-text-to","slug":"fastspeech-fastrobustand-controllable-text-to","title":"FastSpeech: Fast,Robustand Controllable Text-to-Speech","date":"2019-05-22","arxiv_id":null,"n_code_links":11,"syntology":null},{"paper":null,"slug":"a-seq-to-seq-transformer-premised-temporal","title":"A Seq-to-Seq Transformer Premised Temporal Convolutional Network for Chinese Word Segmentation","date":"2019-05-21","arxiv_id":"1905.08454","n_code_links":0,"syntology":null},{"paper":"/paper/lightweight-network-architecture-for-real","slug":"lightweight-network-architecture-for-real","title":"Lightweight Network Architecture for Real-Time Action Recognition","date":"2019-05-21","arxiv_id":"1905.08711","n_code_links":1,"syntology":null},{"paper":"/paper/sample-efficient-text-summarization-using-a","slug":"sample-efficient-text-summarization-using-a","title":"Sample Efficient Text Summarization Using a Single Pre-Trained Transformer","date":"2019-05-21","arxiv_id":"1905.08836","n_code_links":2,"syntology":null},{"paper":null,"slug":"multimodal-transformer-with-multi-view-visual","title":"Multimodal Transformer with Multi-View Visual Representation for Image Captioning","date":"2019-05-20","arxiv_id":"1905.07841","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-attention-span-in-transformers","slug":"adaptive-attention-span-in-transformers","title":"Adaptive Attention Span in Transformers","date":"2019-05-19","arxiv_id":"1905.07799","n_code_links":8,"syntology":null},{"paper":"/paper/bertsel-answer-selection-with-pre-trained","slug":"bertsel-answer-selection-with-pre-trained","title":"BERTSel: Answer Selection with Pre-trained Models","date":"2019-05-18","arxiv_id":"1905.07588","n_code_links":1,"syntology":null},{"paper":"/paper/story-ending-prediction-by-transferable-bert","slug":"story-ending-prediction-by-transferable-bert","title":"Story Ending Prediction by Transferable BERT","date":"2019-05-17","arxiv_id":"1905.07504","n_code_links":1,"syntology":null},{"paper":"/paper/190506596","slug":"190506596","title":"Joint Source-Target Self Attention with Locality Constraints","date":"2019-05-16","arxiv_id":"1905.06596","n_code_links":2,"syntology":null},{"paper":"/paper/hibert-document-level-pre-training-of","slug":"hibert-document-level-pre-training-of","title":"HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization","date":"2019-05-16","arxiv_id":"1905.06566","n_code_links":0,"syntology":null},{"paper":null,"slug":"latent-universal-task-specific-bert","title":"Latent Universal Task-Specific BERT","date":"2019-05-16","arxiv_id":"1905.06638","n_code_links":0,"syntology":null},{"paper":"/paper/behavior-sequence-transformer-for-e-commerce","slug":"behavior-sequence-transformer-for-e-commerce","title":"Behavior Sequence Transformer for E-commerce Recommendation in Alibaba","date":"2019-05-15","arxiv_id":"1905.06874","n_code_links":9,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/190505621","slug":"190505621","title":"Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation","date":"2019-05-14","arxiv_id":"1905.05621","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 2 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":["fastnlp/nlp-dataset","fastnlp/style-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"almost-unsupervised-text-to-speech-and","title":"Almost Unsupervised Text to Speech and Automatic Speech Recognition","date":"2019-05-13","arxiv_id":"1905.06791","n_code_links":0,"syntology":null},{"paper":"/paper/synchronous-bidirectional-neural-machine","slug":"synchronous-bidirectional-neural-machine","title":"Synchronous Bidirectional Neural Machine Translation","date":"2019-05-13","arxiv_id":"1905.04847","n_code_links":2,"syntology":null},{"paper":"/paper/weakly-supervised-caricature-face-parsing","slug":"weakly-supervised-caricature-face-parsing","title":"Weakly-supervised Caricature Face Parsing through Domain Adaptation","date":"2019-05-13","arxiv_id":"1905.05091","n_code_links":1,"syntology":null},{"paper":null,"slug":"densifying-assumed-sparse-tensors-improving","title":"Densifying Assumed-sparse Tensors: Improving Memory Efficiency and MPI Collective Performance during Tensor Accumulation for Parallelized Training of Neural Machine Translation Models","date":"2019-05-10","arxiv_id":"1905.04035","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-modeling-with-deep-transformers","title":"Language Modeling with Deep Transformers","date":"2019-05-10","arxiv_id":"1905.04226","n_code_links":0,"syntology":null},{"paper":"/paper/using-syntactical-and-logical-forms-to","slug":"using-syntactical-and-logical-forms-to","title":"A logical-based corpus for cross-lingual evaluation","date":"2019-05-10","arxiv_id":"1905.05704","n_code_links":1,"syntology":null},{"paper":"/paper/190503381","slug":"190503381","title":"AutoAssist: A Framework to Accelerate Training of Deep Neural Networks","date":"2019-05-08","arxiv_id":"1905.03381","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"photometric-transformer-networks-and-label","title":"Photometric Transformer Networks and Label Adjustment for Breast Density Prediction","date":"2019-05-08","arxiv_id":"1905.02906","n_code_links":0,"syntology":null},{"paper":"/paper/rwth-asr-systems-for-librispeech-hybrid-vs","slug":"rwth-asr-systems-for-librispeech-hybrid-vs","title":"RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation","date":"2019-05-08","arxiv_id":"1905.03072","n_code_links":2,"syntology":null},{"paper":"/paper/unified-language-model-pre-training-for","slug":"unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","n_code_links":9,"syntology":null},{"paper":"/paper/pog-personalized-outfit-generation-for","slug":"pog-personalized-outfit-generation-for","title":"POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion","date":"2019-05-06","arxiv_id":"1905.01866","n_code_links":1,"syntology":null},{"paper":"/paper/discourse-representation-structure-parsing-1","slug":"discourse-representation-structure-parsing-1","title":"Discourse Representation Structure Parsing with Recurrent Neural Networks and the Transformer Model","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-transformer","title":"Graph Transformer","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-agent-dual-learning","slug":"multi-agent-dual-learning","title":"Multi-Agent Dual Learning","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robustness-and-equivariance-of-neural","title":"Robustness and Equivariance of Neural Networks","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"total-style-transfer-with-a-single-feed","title":"Total Style Transfer with a Single Feed-Forward Network","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-better-understanding-of-vector","title":"Towards a better understanding of Vector Quantized Autoencoders","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-xl-language-modeling-with-longer","title":"Transformer-XL: Language Modeling with Longer-Term Dependency","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"very-deep-self-attention-networks-for-end-to","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","date":"2019-04-30","arxiv_id":"1904.13377","n_code_links":0,"syntology":null},{"paper":null,"slug":"softmax-optimizations-for-intel-xeon","title":"Softmax Optimizations for Intel Xeon Processor-based Platforms","date":"2019-04-28","arxiv_id":"1904.12380","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-with-convolutional-context-for","slug":"transformers-with-convolutional-context-for","title":"Transformers with convolutional context for ASR","date":"2019-04-26","arxiv_id":"1904.11660","n_code_links":4,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":null}},{"paper":null,"slug":"low-memory-neural-network-training-a","title":"Low-Memory Neural Network Training: A Technical Report","date":"2019-04-24","arxiv_id":"1904.10631","n_code_links":0,"syntology":null},{"paper":"/paper/190501969","slug":"190501969","title":"Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring","date":"2019-04-22","arxiv_id":"1905.01969","n_code_links":7,"syntology":null},{"paper":"/paper/dynamic-past-and-future-for-neural-machine","slug":"dynamic-past-and-future-for-neural-machine","title":"Dynamic Past and Future for Neural Machine Translation","date":"2019-04-21","arxiv_id":"1904.09646","n_code_links":1,"syntology":null},{"paper":"/paper/190409380","slug":"190409380","title":"Repurposing Entailment for Multi-Hop Question Answering Tasks","date":"2019-04-20","arxiv_id":"1904.09380","n_code_links":4,"syntology":null},{"paper":"/paper/190409408","slug":"190409408","title":"Language Models with Transformers","date":"2019-04-20","arxiv_id":"1904.09408","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"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":{"repos":["cgraywang/gluon-nlp-1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/190409324","slug":"190409324","title":"Mask-Predict: Parallel Decoding of Conditional Masked Language Models","date":"2019-04-19","arxiv_id":"1904.09324","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/Mask-Predict"],"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/real-time-style-transfer-with-strength","slug":"real-time-style-transfer-with-strength","title":"Real-Time Style Transfer With Strength Control","date":"2019-04-18","arxiv_id":"1904.08643","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-the-behaviors-of-bert-in","title":"Understanding the Behaviors of BERT in Ranking","date":"2019-04-16","arxiv_id":"1904.07531","n_code_links":0,"syntology":null},{"paper":"/paper/personalized-context-aware-re-ranking-for-e","slug":"personalized-context-aware-re-ranking-for-e","title":"Personalized Re-ranking for Recommendation","date":"2019-04-15","arxiv_id":"1904.06813","n_code_links":1,"syntology":null},{"paper":"/paper/an-empirical-study-of-spatial-attention","slug":"an-empirical-study-of-spatial-attention","title":"An Empirical Study of Spatial Attention Mechanisms in Deep Networks","date":"2019-04-11","arxiv_id":"1904.05873","n_code_links":1,"syntology":null},{"paper":null,"slug":"identity-preserving-face-recovery-from-1","title":"Identity-preserving Face Recovery from Stylized Portraits","date":"2019-04-07","arxiv_id":"1904.04241","n_code_links":0,"syntology":null},{"paper":null,"slug":"thisiscompetition-at-semeval-2019-task-9-bert","title":"ThisIsCompetition at SemEval-2019 Task 9: BERT is unstable for out-of-domain samples","date":"2019-04-06","arxiv_id":"1904.03339","n_code_links":0,"syntology":null},{"paper":"/paper/token-level-ensemble-distillation-for","slug":"token-level-ensemble-distillation-for","title":"Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion","date":"2019-04-06","arxiv_id":"1904.03446","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-recurrence-for-transformer","title":"Modeling Recurrence for Transformer","date":"2019-04-05","arxiv_id":"1904.03092","n_code_links":0,"syntology":null},{"paper":"/paper/regional-homogeneity-towards-learning","slug":"regional-homogeneity-towards-learning","title":"Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses","date":"2019-04-01","arxiv_id":"1904.00979","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["LiYingwei/Regional-Homogeneity"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-knowledge-based-personalized-product","slug":"towards-knowledge-based-personalized-product","title":"Towards Knowledge-Based Personalized Product Description Generation in E-commerce","date":"2019-03-29","arxiv_id":"1903.12457","n_code_links":4,"syntology":null},{"paper":"/paper/train-sort-explain-learning-to-diagnose","slug":"train-sort-explain-learning-to-diagnose","title":"Train, Sort, Explain: Learning to Diagnose Translation Models","date":"2019-03-28","arxiv_id":"1903.12017","n_code_links":1,"syntology":null},{"paper":null,"slug":"190410045","title":"Automatic Spelling Correction with Transformer for CTC-based End-to-End Speech Recognition","date":"2019-03-27","arxiv_id":"1904.10045","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tune-bert-for-extractive-summarization","slug":"fine-tune-bert-for-extractive-summarization","title":"Fine-tune BERT for Extractive Summarization","date":"2019-03-25","arxiv_id":"1903.10318","n_code_links":12,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nlpyang/BertSum"],"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":"knowledge-driven-encode-retrieve-paraphrase","title":"Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation","date":"2019-03-25","arxiv_id":"1903.10122","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-multi-level-information-for-dialogue","title":"Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer","date":"2019-03-21","arxiv_id":"1903.08953","n_code_links":0,"syntology":null},{"paper":null,"slug":"linguistic-knowledge-and-transferability-of","title":"Linguistic Knowledge and Transferability of Contextual Representations","date":"2019-03-21","arxiv_id":"1903.08855","n_code_links":0,"syntology":null},{"paper":"/paper/selective-attention-for-context-aware-neural","slug":"selective-attention-for-context-aware-neural","title":"Selective Attention for Context-aware Neural Machine Translation","date":"2019-03-21","arxiv_id":"1903.08788","n_code_links":1,"syntology":null},{"paper":"/paper/cloze-driven-pretraining-of-self-attention","slug":"cloze-driven-pretraining-of-self-attention","title":"Cloze-driven Pretraining of Self-attention Networks","date":"2019-03-19","arxiv_id":"1903.07785","n_code_links":0,"syntology":null},{"paper":"/paper/neutron-an-implementation-of-the-transformer","slug":"neutron-an-implementation-of-the-transformer","title":"Neutron: An Implementation of the Transformer Translation Model and its Variants","date":"2019-03-18","arxiv_id":"1903.07402","n_code_links":2,"syntology":null},{"paper":null,"slug":"stnreid-deep-convolutional-networks-with","title":"STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification","date":"2019-03-17","arxiv_id":"1903.07072","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-patent-landscaping-model-using","title":"Deep Patent Landscaping Model Using Transformer and Graph Embedding","date":"2019-03-14","arxiv_id":"1903.05823","n_code_links":0,"syntology":null},{"paper":"/paper/episodic-memory-reader-learning-what-to","slug":"episodic-memory-reader-learning-what-to","title":"Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data","date":"2019-03-14","arxiv_id":"1903.06164","n_code_links":1,"syntology":null},{"paper":"/paper/communication-efficient-distributed-sgd-with","slug":"communication-efficient-distributed-sgd-with","title":"Communication-efficient distributed SGD with Sketching","date":"2019-03-12","arxiv_id":"1903.04488","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":["dhroth/sketchedsgd"],"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":"scene-memory-transformer-for-embodied-agents","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","date":"2019-03-09","arxiv_id":"1903.03878","n_code_links":0,"syntology":null},{"paper":null,"slug":"dixit-interactive-visual-storytelling-via","title":"Dixit: Interactive Visual Storytelling via Term Manipulation","date":"2019-03-06","arxiv_id":"1903.02230","n_code_links":0,"syntology":null},{"paper":null,"slug":"gq-stn-optimizing-one-shot-grasp-detection","title":"GQ-STN: Optimizing One-Shot Grasp Detection based on Robustness Classifier","date":"2019-03-06","arxiv_id":"1903.02489","n_code_links":0,"syntology":null},{"paper":"/paper/self-adversarial-variational-autoencoder-with","slug":"self-adversarial-variational-autoencoder-with","title":"adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection","date":"2019-03-03","arxiv_id":"1903.00904","n_code_links":2,"syntology":null},{"paper":"/paper/frequency-domain-transformer-networks-for","slug":"frequency-domain-transformer-networks-for","title":"Frequency Domain Transformer Networks for Video Prediction","date":"2019-03-01","arxiv_id":"1903.00271","n_code_links":1,"syntology":null},{"paper":"/paper/star-transformer","slug":"star-transformer","title":"Star-Transformer","date":"2019-02-25","arxiv_id":"1902.09113","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["dmlc/dgl"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"dynamic-layer-aggregation-for-neural-machine","title":"Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement","date":"2019-02-15","arxiv_id":"1902.05770","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-reading-comprehension-for-answer-re","title":"Machine Reading Comprehension for Answer Re-Ranking in Customer Support Chatbots","date":"2019-02-12","arxiv_id":"1902.04574","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-deep-image-clustering-with-spatial","title":"Improving Deep Image Clustering With Spatial Transformer Layers","date":"2019-02-09","arxiv_id":"1902.05401","n_code_links":0,"syntology":null},{"paper":null,"slug":"insertion-transformer-flexible-sequence","title":"Insertion Transformer: Flexible Sequence Generation via Insertion Operations","date":"2019-02-08","arxiv_id":"1902.03249","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphastar-an-evolutionary-computation","title":"AlphaStar: An Evolutionary Computation Perspective","date":"2019-02-05","arxiv_id":"1902.01724","n_code_links":0,"syntology":null},{"paper":null,"slug":"insertion-based-decoding-with-automatically","title":"Insertion-based Decoding with automatically Inferred Generation Order","date":"2019-02-04","arxiv_id":"1902.01370","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-efficient-transfer-learning-for-nlp","slug":"parameter-efficient-transfer-learning-for-nlp","title":"Parameter-Efficient Transfer Learning for NLP","date":"2019-02-02","arxiv_id":"1902.00751","n_code_links":17,"syntology":{"ran":14,"of":22,"n_ran_checked":14,"n_instrument":0,"unverified":8,"pointer_only":3,"phrase":"14 ran (of which 3 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["google-research/adapter-bert"],"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/adding-interpretable-attention-to-neural","slug":"adding-interpretable-attention-to-neural","title":"Adding Interpretable Attention to Neural Translation Models Improves Word Alignment","date":"2019-01-31","arxiv_id":"1901.11359","n_code_links":1,"syntology":null},{"paper":"/paper/multi-task-deep-neural-networks-for-natural","slug":"multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","arxiv_id":"1901.11504","n_code_links":7,"syntology":{"ran":9,"of":13,"n_ran_checked":6,"n_instrument":3,"unverified":4,"pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["namisan/mt-dnn"],"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/the-second-conversational-intelligence","slug":"the-second-conversational-intelligence","title":"The Second Conversational Intelligence Challenge (ConvAI2)","date":"2019-01-31","arxiv_id":"1902.00098","n_code_links":2,"syntology":null},{"paper":"/paper/the-evolved-transformer","slug":"the-evolved-transformer","title":"The Evolved Transformer","date":"2019-01-30","arxiv_id":"1901.11117","n_code_links":3,"syntology":null},{"paper":null,"slug":"self-attentive-model-for-headline-generation","title":"Self-Attentive Model for Headline Generation","date":"2019-01-23","arxiv_id":"1901.07786","n_code_links":0,"syntology":null},{"paper":"/paper/transfertransfo-a-transfer-learning-approach","slug":"transfertransfo-a-transfer-learning-approach","title":"TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents","date":"2019-01-23","arxiv_id":"1901.08149","n_code_links":23,"syntology":{"ran":18,"of":26,"n_ran_checked":11,"n_instrument":7,"unverified":8,"pointer_only":7,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified","official":null}}],"record_sha256":"d68e596dcdae3056c7df1b47df4ef5c51be27cbd3f6de37d62e8a3ee814234f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}