{"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/softmax/papers/337","list_of":"/method/softmax","method":"Softmax","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":337,"pages_in_order":375,"rows_per_page":100,"rows":[33601,33700],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/336","next":"/method/softmax/papers/338","papers":[{"paper":null,"slug":"bilingual-text-extraction-as-reading","title":"Bilingual Text Extraction as Reading Comprehension","date":"2020-04-29","arxiv_id":"2004.14517","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-perceived-emotions-in-hurricane","slug":"detecting-perceived-emotions-in-hurricane","title":"Detecting Perceived Emotions in Hurricane Disasters","date":"2020-04-29","arxiv_id":"2004.14299","n_code_links":1,"syntology":null},{"paper":"/paper/distantly-supervised-neural-relation","slug":"distantly-supervised-neural-relation","title":"Distantly-Supervised Neural Relation Extraction with Side Information using BERT","date":"2020-04-29","arxiv_id":"2004.14443","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-neural-language-models-show-preferences","title":"Do Neural Language Models Show Preferences for Syntactic Formalisms?","date":"2020-04-29","arxiv_id":"2004.14096","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-document-re-ranking-for","slug":"efficient-document-re-ranking-for","title":"Efficient Document Re-Ranking for Transformers by Precomputing Term Representations","date":"2020-04-29","arxiv_id":"2004.14255","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-slot-alignment-and-recognition-for","slug":"end-to-end-slot-alignment-and-recognition-for","title":"End-to-End Slot Alignment and Recognition for Cross-Lingual NLU","date":"2020-04-29","arxiv_id":"2004.14353","n_code_links":3,"syntology":null},{"paper":"/paper/geppetto-carves-italian-into-a-language-model","slug":"geppetto-carves-italian-into-a-language-model","title":"GePpeTto Carves Italian into a Language Model","date":"2020-04-29","arxiv_id":"2004.14253","n_code_links":1,"syntology":null},{"paper":"/paper/image-captioning-through-image-transformer","slug":"image-captioning-through-image-transformer","title":"Image Captioning through Image Transformer","date":"2020-04-29","arxiv_id":"2004.14231","n_code_links":2,"syntology":null},{"paper":"/paper/image-morphing-with-perceptual-constraints","slug":"image-morphing-with-perceptual-constraints","title":"Image Morphing with Perceptual Constraints and STN Alignment","date":"2020-04-29","arxiv_id":"2004.14071","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-better-universal-representations","title":"BURT: BERT-inspired Universal Representation from Twin Structure","date":"2020-04-29","arxiv_id":"2004.13947","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiresolution-and-multimodal-speech","title":"Multiresolution and Multimodal Speech Recognition with Transformers","date":"2020-04-29","arxiv_id":"2004.14840","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-training-is-almost-all-you-need-an","title":"Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning","date":"2020-04-29","arxiv_id":"2004.14074","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-pre-trained-models-for-chinese","slug":"revisiting-pre-trained-models-for-chinese","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","date":"2020-04-29","arxiv_id":"2004.13922","n_code_links":6,"syntology":{"ran":21,"of":35,"n_ran_checked":16,"n_instrument":5,"unverified":14,"pointer_only":4,"phrase":"21 ran (of which 1 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified","official":{"repos":["ymcui/MacBERT"],"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/teaching-cameras-to-feel-estimating-tactile","slug":"teaching-cameras-to-feel-estimating-tactile","title":"Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From Images","date":"2020-04-29","arxiv_id":"2004.14487","n_code_links":1,"syntology":null},{"paper":"/paper/textattack-a-framework-for-adversarial","slug":"textattack-a-framework-for-adversarial","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","date":"2020-04-29","arxiv_id":"2005.05909","n_code_links":2,"syntology":null},{"paper":"/paper/towards-character-level-transformer-nmt-by","slug":"towards-character-level-transformer-nmt-by","title":"Towards Reasonably-Sized Character-Level Transformer NMT by Finetuning Subword Systems","date":"2020-04-29","arxiv_id":"2004.14280","n_code_links":2,"syntology":null},{"paper":"/paper/training-curricula-for-open-domain-answer-re","slug":"training-curricula-for-open-domain-answer-re","title":"Training Curricula for Open Domain Answer Re-Ranking","date":"2020-04-29","arxiv_id":"2004.14269","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-happens-to-bert-embeddings-during-fine","title":"What Happens To BERT Embeddings During Fine-tuning?","date":"2020-04-29","arxiv_id":"2004.14448","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-region-of-interest-extraction-layer","slug":"a-novel-region-of-interest-extraction-layer","title":"A novel Region of Interest Extraction Layer for Instance Segmentation","date":"2020-04-28","arxiv_id":"2004.13665","n_code_links":5,"syntology":null},{"paper":"/paper/dombert-domain-oriented-language-model-for","slug":"dombert-domain-oriented-language-model-for","title":"DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis","date":"2020-04-28","arxiv_id":"2004.13816","n_code_links":1,"syntology":null},{"paper":"/paper/dru-net-an-efficient-deep-convolutional","slug":"dru-net-an-efficient-deep-convolutional","title":"DRU-net: An Efficient Deep Convolutional Neural Network for Medical Image Segmentation","date":"2020-04-28","arxiv_id":"2004.13453","n_code_links":1,"syntology":null},{"paper":null,"slug":"earl-speedup-transformer-based-rankers-with","title":"Modularized Transfomer-based Ranking Framework","date":"2020-04-28","arxiv_id":"2004.13313","n_code_links":0,"syntology":null},{"paper":null,"slug":"extending-multilingual-bert-to-low-resource","title":"Extending Multilingual BERT to Low-Resource Languages","date":"2020-04-28","arxiv_id":"2004.13640","n_code_links":0,"syntology":null},{"paper":"/paper/finding-macro-actions-with-disentangled","slug":"finding-macro-actions-with-disentangled","title":"Efficient Black-Box Planning Using Macro-Actions with Focused Effects","date":"2020-04-28","arxiv_id":"2004.13242","n_code_links":2,"syntology":{"ran":8,"of":13,"n_ran_checked":8,"n_instrument":0,"unverified":5,"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) · 5 unverified","official":{"repos":["camall3n/focused-macros","camall3n/skills-for-planning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"identification-of-cervical-pathology-using","title":"Identification of Cervical Pathology using Adversarial Neural Networks","date":"2020-04-28","arxiv_id":"2004.13406","n_code_links":0,"syntology":null},{"paper":"/paper/joint-keyphrase-chunking-and-salience-ranking","slug":"joint-keyphrase-chunking-and-salience-ranking","title":"Capturing Global Informativeness in Open Domain Keyphrase Extraction","date":"2020-04-28","arxiv_id":"2004.13639","n_code_links":2,"syntology":null},{"paper":"/paper/kungfupanda-at-semeval-2020-task-12-bert","slug":"kungfupanda-at-semeval-2020-task-12-bert","title":"Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection","date":"2020-04-28","arxiv_id":"2004.13432","n_code_links":1,"syntology":null},{"paper":null,"slug":"multinomial-logit-processes-and-preference","title":"Multinomial logit processes and preference discovery: inside and outside the black box","date":"2020-04-28","arxiv_id":"2004.13376","n_code_links":0,"syntology":null},{"paper":"/paper/r-3-reverse-retrieve-and-rank-for-sarcasm","slug":"r-3-reverse-retrieve-and-rank-for-sarcasm","title":"$R^3$: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge","date":"2020-04-28","arxiv_id":"2004.13248","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":null}},{"paper":null,"slug":"scelmo-source-code-embeddings-from-language-1","title":"SCELMo: Source Code Embeddings from Language Models","date":"2020-04-28","arxiv_id":"2004.13214","n_code_links":0,"syntology":null},{"paper":"/paper/scheduled-drophead-a-regularization-method","slug":"scheduled-drophead-a-regularization-method","title":"Scheduled DropHead: A Regularization Method for Transformer Models","date":"2020-04-28","arxiv_id":"2004.13342","n_code_links":1,"syntology":null},{"paper":"/paper/vd-bert-a-unified-vision-and-dialog","slug":"vd-bert-a-unified-vision-and-dialog","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","date":"2020-04-28","arxiv_id":"2004.13278","n_code_links":1,"syntology":{"ran":2,"of":11,"n_ran_checked":2,"n_instrument":0,"unverified":9,"pointer_only":0,"phrase":"2 ran (of which 1 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) · 9 unverified","official":{"repos":["salesforce/VD-BERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-scoping-review-of-transfer-learning","title":"A scoping review of transfer learning research on medical image analysis using ImageNet","date":"2020-04-27","arxiv_id":"2004.13175","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmenting-transformers-with-knn-based-1","title":"Augmenting Transformers with KNN-Based Composite Memory for Dialogue","date":"2020-04-27","arxiv_id":"2004.12744","n_code_links":0,"syntology":null},{"paper":"/paper/colbert-efficient-and-effective-passage","slug":"colbert-efficient-and-effective-passage","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","date":"2020-04-27","arxiv_id":"2004.12832","n_code_links":9,"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":["stanford-futuredata/ColBERT"],"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/colbert-using-bert-sentence-embedding-for","slug":"colbert-using-bert-sentence-embedding-for","title":"ColBERT: Using BERT Sentence Embedding in Parallel Neural Networks for Computational Humor","date":"2020-04-27","arxiv_id":"2004.12765","n_code_links":4,"syntology":null},{"paper":"/paper/deebert-dynamic-early-exiting-for","slug":"deebert-dynamic-early-exiting-for","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","date":"2020-04-27","arxiv_id":"2004.12993","n_code_links":3,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["castorini/deebert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"explicitly-modeling-adaptive-depths-for","title":"Faster Depth-Adaptive Transformers","date":"2020-04-27","arxiv_id":"2004.13542","n_code_links":0,"syntology":null},{"paper":"/paper/lexically-constrained-neural-machine","slug":"lexically-constrained-neural-machine","title":"Lexically Constrained Neural Machine Translation with Levenshtein Transformer","date":"2020-04-27","arxiv_id":"2004.12681","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["raymondhs/constrained-levt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lightpaff-a-two-stage-distillation-framework-1","title":"LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning","date":"2020-04-27","arxiv_id":"2004.12817","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-importance-of-word-and-sentence","slug":"on-the-importance-of-word-and-sentence","title":"On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification","date":"2020-04-27","arxiv_id":"2004.12617","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":["HKUST-KnowComp/BMGF-RoBERTa"],"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/recall-and-learn-fine-tuning-deep-pretrained","slug":"recall-and-learn-fine-tuning-deep-pretrained","title":"Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting","date":"2020-04-27","arxiv_id":"2004.12651","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-problem-of-fragmented-occlusion-in-object","title":"The Problem of Fragmented Occlusion in Object Detection","date":"2020-04-27","arxiv_id":"2004.13076","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-discourse-relations-in-language","title":"Assessing Discourse Relations in Language Generation from GPT-2","date":"2020-04-26","arxiv_id":"2004.12506","n_code_links":0,"syntology":null},{"paper":null,"slug":"autohr-a-strong-end-to-end-baseline-for","title":"AutoHR: A Strong End-to-end Baseline for Remote Heart Rate Measurement with Neural Searching","date":"2020-04-26","arxiv_id":"2004.12292","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-512-tokens-siamese-multi-depth","slug":"beyond-512-tokens-siamese-multi-depth","title":"Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching","date":"2020-04-26","arxiv_id":"2004.12297","n_code_links":1,"syntology":null},{"paper":"/paper/causal-mediation-analysis-for-interpreting","slug":"causal-mediation-analysis-for-interpreting","title":"Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias","date":"2020-04-26","arxiv_id":"2004.12265","n_code_links":1,"syntology":null},{"paper":null,"slug":"challenge-closed-book-science-exam-a-meta","title":"Challenge Closed-book Science Exam: A Meta-learning Based Question Answering System","date":"2020-04-26","arxiv_id":"2004.12303","n_code_links":0,"syntology":null},{"paper":null,"slug":"choppy-cut-transformer-for-ranked-list","title":"Choppy: Cut Transformer For Ranked List Truncation","date":"2020-04-26","arxiv_id":"2004.13012","n_code_links":0,"syntology":null},{"paper":null,"slug":"classification-of-cuisines-from-sequentially","title":"Classification of Cuisines from Sequentially Structured Recipes","date":"2020-04-26","arxiv_id":"2004.14165","n_code_links":0,"syntology":null},{"paper":null,"slug":"experiments-with-lvt-and-fre-for-transformer","title":"Experiments with LVT and FRE for Transformer model","date":"2020-04-26","arxiv_id":"2004.12495","n_code_links":0,"syntology":null},{"paper":null,"slug":"masking-as-an-efficient-alternative-to","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","date":"2020-04-26","arxiv_id":"2004.12406","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-modeling-units-of-transformer","title":"Research on Modeling Units of Transformer Transducer for Mandarin Speech Recognition","date":"2020-04-26","arxiv_id":"2004.13522","n_code_links":0,"syntology":null},{"paper":"/paper/spellgcn-incorporating-phonological-and","slug":"spellgcn-incorporating-phonological-and","title":"SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check","date":"2020-04-26","arxiv_id":"2004.14166","n_code_links":1,"syntology":null},{"paper":"/paper/all-word-embeddings-from-one-embedding","slug":"all-word-embeddings-from-one-embedding","title":"All Word Embeddings from One Embedding","date":"2020-04-25","arxiv_id":"2004.12073","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["takase/alone_seq2seq"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/autotune-automatically-tuning-convolutional","slug":"autotune-automatically-tuning-convolutional","title":"AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning","date":"2020-04-25","arxiv_id":"2005.02165","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-word-embeddings-and-n-grams-for","title":"Combining Word Embeddings and N-grams for Unsupervised Document Summarization","date":"2020-04-25","arxiv_id":"2004.14119","n_code_links":0,"syntology":null},{"paper":"/paper/deep-multimodal-neural-architecture-search","slug":"deep-multimodal-neural-architecture-search","title":"Deep Multimodal Neural Architecture Search","date":"2020-04-25","arxiv_id":"2004.12070","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-safety-of-vulnerable-road-users-by","slug":"on-the-safety-of-vulnerable-road-users-by","title":"On the safety of vulnerable road users by cyclist orientation detection using Deep Learning","date":"2020-04-25","arxiv_id":"2004.11909","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-the-contextualization-of-word","title":"Quantifying the Contextualization of Word Representations with Semantic Class Probing","date":"2020-04-25","arxiv_id":"2004.12198","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-light-cnn-for-detecting-covid-19-from-ct","title":"A Light CNN for detecting COVID-19 from CT scans of the chest","date":"2020-04-24","arxiv_id":"2004.12837","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-systematic-search-over-deep-convolutional","title":"A Systematic Search over Deep Convolutional Neural Network Architectures for Screening Chest Radiographs","date":"2020-04-24","arxiv_id":"2004.11693","n_code_links":0,"syntology":null},{"paper":"/paper/a-tailored-pre-training-model-for-task","slug":"a-tailored-pre-training-model-for-task","title":"A Tailored Pre-Training Model for Task-Oriented Dialog Generation","date":"2020-04-24","arxiv_id":"2004.13835","n_code_links":1,"syntology":null},{"paper":"/paper/collecting-entailment-data-for-pretraining","slug":"collecting-entailment-data-for-pretraining","title":"New Protocols and Negative Results for Textual Entailment Data Collection","date":"2020-04-24","arxiv_id":"2004.11997","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextualized-representations-using-textual","title":"Contextualized Representations Using Textual Encyclopedic Knowledge","date":"2020-04-24","arxiv_id":"2004.12006","n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-information-retrieval-with-bert","slug":"cross-lingual-information-retrieval-with-bert","title":"Cross-lingual Information Retrieval with BERT","date":"2020-04-24","arxiv_id":"2004.13005","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-annealing-for-informal-language","title":"Data Annealing for Informal Language Understanding Tasks","date":"2020-04-24","arxiv_id":"2004.13833","n_code_links":0,"syntology":null},{"paper":"/paper/flat-chinese-ner-using-flat-lattice","slug":"flat-chinese-ner-using-flat-lattice","title":"FLAT: Chinese NER Using Flat-Lattice Transformer","date":"2020-04-24","arxiv_id":"2004.11795","n_code_links":1,"syntology":null},{"paper":"/paper/lite-transformer-with-long-short-range","slug":"lite-transformer-with-long-short-range","title":"Lite Transformer with Long-Short Range Attention","date":"2020-04-24","arxiv_id":"2004.11886","n_code_links":2,"syntology":null},{"paper":"/paper/on-sparsifying-encoder-outputs-in-sequence-to","slug":"on-sparsifying-encoder-outputs-in-sequence-to","title":"On Sparsifying Encoder Outputs in Sequence-to-Sequence Models","date":"2020-04-24","arxiv_id":"2004.11854","n_code_links":1,"syntology":null},{"paper":"/paper/probabilistically-masked-language-model","slug":"probabilistically-masked-language-model","title":"Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order","date":"2020-04-24","arxiv_id":"2004.11579","n_code_links":3,"syntology":{"ran":21,"of":35,"n_ran_checked":12,"n_instrument":9,"unverified":14,"pointer_only":29,"phrase":"21 ran (of which 1 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 3 violated, 5 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified","official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":1,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"quantization-of-deep-neural-networks-for","title":"Quantization of Deep Neural Networks for Accumulator-constrained Processors","date":"2020-04-24","arxiv_id":"2004.11783","n_code_links":0,"syntology":null},{"paper":"/paper/syntactic-data-augmentation-increases","slug":"syntactic-data-augmentation-increases","title":"Syntactic Data Augmentation Increases Robustness to Inference Heuristics","date":"2020-04-24","arxiv_id":"2004.11999","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":["aatlantise/syntactic-augmentation-nli"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-inception-team-at-nsurl-2019-task-8","slug":"the-inception-team-at-nsurl-2019-task-8","title":"The Inception Team at NSURL-2019 Task 8: Semantic Question Similarity in Arabic","date":"2020-04-24","arxiv_id":"2004.11964","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-when-spatial-transformer","slug":"understanding-when-spatial-transformer","title":"Understanding when spatial transformer networks do not support invariance, and what to do about it","date":"2020-04-24","arxiv_id":"2004.11678","n_code_links":1,"syntology":null},{"paper":"/paper/automated-diagnosis-of-covid-19-with-limited","slug":"automated-diagnosis-of-covid-19-with-limited","title":"Automated diagnosis of COVID-19 with limited posteroanterior chest X-ray images using fine-tuned deep neural networks","date":"2020-04-23","arxiv_id":"2004.11676","n_code_links":1,"syntology":null},{"paper":"/paper/depth-wise-neural-architecture-search","slug":"depth-wise-neural-architecture-search","title":"Stage-Wise Neural Architecture Search","date":"2020-04-23","arxiv_id":"2004.11178","n_code_links":2,"syntology":null},{"paper":null,"slug":"end-to-end-speech-to-dialog-act-recognition","title":"End-to-end speech-to-dialog-act recognition","date":"2020-04-23","arxiv_id":"2004.11419","n_code_links":0,"syntology":null},{"paper":"/paper/moltrans-molecular-interaction-transformer","slug":"moltrans-molecular-interaction-transformer","title":"MolTrans: Molecular Interaction Transformer for Drug Target Interaction Prediction","date":"2020-04-23","arxiv_id":"2004.11424","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-adversarial-examples-for-biomedical-nlp","title":"On Adversarial Examples for Biomedical NLP Tasks","date":"2020-04-23","arxiv_id":"2004.11157","n_code_links":0,"syntology":null},{"paper":null,"slug":"same-side-stance-classification-task","title":"Same Side Stance Classification Task: Facilitating Argument Stance Classification by Fine-tuning a BERT Model","date":"2020-04-23","arxiv_id":"2004.11163","n_code_links":0,"syntology":null},{"paper":"/paper/self-attention-attribution-interpreting","slug":"self-attention-attribution-interpreting","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","date":"2020-04-23","arxiv_id":"2004.11207","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":["YRdddream/attattr"],"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":"uhh-lt-lt2-at-semeval-2020-task-12-fine","title":"UHH-LT at SemEval-2020 Task 12: Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection","date":"2020-04-23","arxiv_id":"2004.11493","n_code_links":0,"syntology":null},{"paper":"/paper/yolov4-optimal-speed-and-accuracy-of-object","slug":"yolov4-optimal-speed-and-accuracy-of-object","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","date":"2020-04-23","arxiv_id":"2004.10934","n_code_links":223,"syntology":{"ran":142,"of":184,"n_ran_checked":133,"n_instrument":9,"unverified":42,"pointer_only":21,"phrase":"142 ran (of which 0 constructed an object rather than computing a result; 133 with no instrument failure: 6 honoured, 0 violated, 127 with no contract checked; 9 where Syntology's instrument failed) · 42 unverified","official":{"repos":["AlexeyAB/darknet"],"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":"automatic-detection-of-coronavirus-disease-1","title":"Automatic Detection of Coronavirus Disease (COVID-19) in X-ray and CT Images: A Machine Learning-Based Approach","date":"2020-04-22","arxiv_id":"2004.10641","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-polyp-segmentation-using","title":"Automatic Polyp Segmentation Using Convolutional Neural Networks","date":"2020-04-22","arxiv_id":"2004.10792","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynet-dynamic-convolution-for-accelerating-1","title":"DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks","date":"2020-04-22","arxiv_id":"2004.10694","n_code_links":0,"syntology":null},{"paper":null,"slug":"keyphrase-prediction-with-pre-trained","title":"Keyphrase Prediction With Pre-trained Language Model","date":"2020-04-22","arxiv_id":"2004.10462","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-classify-intents-and-slot-labels","title":"Learning to Classify Intents and Slot Labels Given a Handful of Examples","date":"2020-04-22","arxiv_id":"2004.10793","n_code_links":0,"syntology":null},{"paper":"/paper/logical-natural-language-generation-from-open","slug":"logical-natural-language-generation-from-open","title":"Logical Natural Language Generation from Open-Domain Tables","date":"2020-04-22","arxiv_id":"2004.10404","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["wenhuchen/LogicNLG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/residual-energy-based-models-for-text-1","slug":"residual-energy-based-models-for-text-1","title":"Residual Energy-Based Models for Text Generation","date":"2020-04-22","arxiv_id":"2004.11714","n_code_links":1,"syntology":null},{"paper":"/paper/towards-a-competitive-end-to-end-speech","slug":"towards-a-competitive-end-to-end-speech","title":"Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription","date":"2020-04-22","arxiv_id":"2004.10799","n_code_links":1,"syntology":null},{"paper":"/paper/yoga-82-a-new-dataset-for-fine-grained","slug":"yoga-82-a-new-dataset-for-fine-grained","title":"Yoga-82: A New Dataset for Fine-grained Classification of Human Poses","date":"2020-04-22","arxiv_id":"2004.10362","n_code_links":1,"syntology":null},{"paper":"/paper/a-generic-network-compression-framework-for","slug":"a-generic-network-compression-framework-for","title":"A Generic Network Compression Framework for Sequential Recommender Systems","date":"2020-04-21","arxiv_id":"2004.13139","n_code_links":1,"syntology":null},{"paper":"/paper/attention-module-is-not-only-a-weight","slug":"attention-module-is-not-only-a-weight","title":"Attention is Not Only a Weight: Analyzing Transformers with Vector Norms","date":"2020-04-21","arxiv_id":"2004.10102","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gorokoba560/norm-analysis-of-transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/bert-attack-adversarial-attack-against-bert","slug":"bert-attack-adversarial-attack-against-bert","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","date":"2020-04-21","arxiv_id":"2004.09984","n_code_links":4,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["LinyangLee/BERT-Attack","QData/TextAttack"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","unlocated"]}}},{"paper":"/paper/contextual-neural-machine-translation","slug":"contextual-neural-machine-translation","title":"Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns","date":"2020-04-21","arxiv_id":"2004.09894","n_code_links":1,"syntology":null},{"paper":"/paper/diet-lightweight-language-understanding-for","slug":"diet-lightweight-language-understanding-for","title":"DIET: Lightweight Language Understanding for Dialogue Systems","date":"2020-04-21","arxiv_id":"2004.09936","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["RasaHQ/DIET-paper"],"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":"domain-guided-task-decomposition-with-self","title":"Domain-Guided Task Decomposition with Self-Training for Detecting Personal Events in Social Media","date":"2020-04-21","arxiv_id":"2004.10201","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-effectiveness-of","title":"Investigating the Effectiveness of Representations Based on Pretrained Transformer-based Language Models in Active Learning for Labelling Text Datasets","date":"2020-04-21","arxiv_id":"2004.13138","n_code_links":0,"syntology":null}],"record_sha256":"aadaa2b9838f5b195bb9d41abff1db91636dbbdb20c663b74ca0da509ab382a9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}