{"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/289","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":289,"pages_in_order":375,"rows_per_page":100,"rows":[28801,28900],"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/288","next":"/method/softmax/papers/290","papers":[{"paper":"/paper/a-three-stage-learning-framework-for-low","slug":"a-three-stage-learning-framework-for-low","title":"A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation","date":"2021-09-09","arxiv_id":"2109.04096","n_code_links":1,"syntology":{"ran":18,"of":27,"n_ran_checked":12,"n_instrument":6,"unverified":9,"pointer_only":5,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 9 unverified","official":{"repos":["neukg/kat-tslf"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/all-bark-and-no-bite-rogue-dimensions-in","slug":"all-bark-and-no-bite-rogue-dimensions-in","title":"All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality","date":"2021-09-09","arxiv_id":"2109.04404","n_code_links":1,"syntology":null},{"paper":"/paper/bag-of-tricks-for-optimizing-transformer","slug":"bag-of-tricks-for-optimizing-transformer","title":"Bag of Tricks for Optimizing Transformer Efficiency","date":"2021-09-09","arxiv_id":"2109.04030","n_code_links":1,"syntology":null},{"paper":"/paper/bert-mbert-or-bibert-a-study-on","slug":"bert-mbert-or-bibert-a-study-on","title":"BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation","date":"2021-09-09","arxiv_id":"2109.04588","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["fe1ixxu/BiBERT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"dan-decentralized-attention-based-neural","title":"DAN: Decentralized Attention-based Neural Network for the MinMax Multiple Traveling Salesman Problem","date":"2021-09-09","arxiv_id":"2109.04205","n_code_links":0,"syntology":null},{"paper":null,"slug":"erfact-non-monotonic-smooth-trainable","title":"ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions","date":"2021-09-09","arxiv_id":"2109.04386","n_code_links":0,"syntology":null},{"paper":"/paper/esimcse-enhanced-sample-building-method-for","slug":"esimcse-enhanced-sample-building-method-for","title":"ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding","date":"2021-09-09","arxiv_id":"2109.04380","n_code_links":2,"syntology":null},{"paper":"/paper/generalised-unsupervised-domain-adaptation-of","slug":"generalised-unsupervised-domain-adaptation-of","title":"Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection","date":"2021-09-09","arxiv_id":"2109.04292","n_code_links":1,"syntology":null},{"paper":"/paper/generic-resources-are-what-you-need-style","slug":"generic-resources-are-what-you-need-style","title":"Generic resources are what you need: Style transfer tasks without task-specific parallel training data","date":"2021-09-09","arxiv_id":"2109.04543","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-based-decoding-for-task-oriented","title":"Graph-Based Decoding for Task Oriented Semantic Parsing","date":"2021-09-09","arxiv_id":"2109.04587","n_code_links":0,"syntology":null},{"paper":"/paper/improving-video-text-retrieval-by-multi","slug":"improving-video-text-retrieval-by-multi","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","date":"2021-09-09","arxiv_id":"2109.04290","n_code_links":2,"syntology":null},{"paper":"/paper/kelm-knowledge-enhanced-pre-trained-language","slug":"kelm-knowledge-enhanced-pre-trained-language","title":"KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs","date":"2021-09-09","arxiv_id":"2109.04223","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nlp-anonymous-happy/anonymous-kg-guided-nlp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mate-multi-view-attention-for-table","slug":"mate-multi-view-attention-for-table","title":"MATE: Multi-view Attention for Table Transformer Efficiency","date":"2021-09-09","arxiv_id":"2109.04312","n_code_links":1,"syntology":null},{"paper":null,"slug":"medically-aware-gpt-3-as-a-data-generator-for","title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization","date":"2021-09-09","arxiv_id":"2110.07356","n_code_links":0,"syntology":null},{"paper":null,"slug":"mining-points-of-interest-via-address","title":"Mining Points of Interest via Address Embeddings: An Unsupervised Approach","date":"2021-09-09","arxiv_id":"2109.04467","n_code_links":0,"syntology":null},{"paper":"/paper/multi-granularity-textual-adversarial-attack","slug":"multi-granularity-textual-adversarial-attack","title":"Multi-granularity Textual Adversarial Attack with Behavior Cloning","date":"2021-09-09","arxiv_id":"2109.04367","n_code_links":1,"syntology":null},{"paper":"/paper/thinking-clearly-talking-fast-concept-guided","slug":"thinking-clearly-talking-fast-concept-guided","title":"Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems","date":"2021-09-09","arxiv_id":"2109.04084","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":2,"phrase":"5 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; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["rowitzou/cg-nar"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"txt-crossmodal-end-to-end-learning-with","title":"TxT: Crossmodal End-to-End Learning with Transformers","date":"2021-09-09","arxiv_id":"2109.04422","n_code_links":0,"syntology":null},{"paper":"/paper/uctransnet-rethinking-the-skip-connections-in","slug":"uctransnet-rethinking-the-skip-connections-in","title":"UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer","date":"2021-09-09","arxiv_id":"2109.04335","n_code_links":3,"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":["mcgregorwwww/uctransnet"],"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":"/paper/variational-latent-state-gpt-for-semi","slug":"variational-latent-state-gpt-for-semi","title":"Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems","date":"2021-09-09","arxiv_id":"2109.04314","n_code_links":2,"syntology":null},{"paper":"/paper/word-level-coreference-resolution","slug":"word-level-coreference-resolution","title":"Word-Level Coreference Resolution","date":"2021-09-09","arxiv_id":"2109.04127","n_code_links":1,"syntology":null},{"paper":null,"slug":"ensemble-fine-tuned-mbert-for-translation","title":"Ensemble Fine-tuned mBERT for Translation Quality Estimation","date":"2021-09-08","arxiv_id":"2109.03914","n_code_links":0,"syntology":null},{"paper":"/paper/forget-me-not-a-gentle-reminder-to-mind-the","slug":"forget-me-not-a-gentle-reminder-to-mind-the","title":"Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP","date":"2021-09-08","arxiv_id":"2109.03777","n_code_links":2,"syntology":null},{"paper":"/paper/label-verbalization-and-entailment-for","slug":"label-verbalization-and-entailment-for","title":"Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction","date":"2021-09-08","arxiv_id":"2109.03659","n_code_links":1,"syntology":null},{"paper":null,"slug":"mask-is-all-you-need-rethinking-mask-r-cnn","title":"Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection","date":"2021-09-08","arxiv_id":"2109.03426","n_code_links":0,"syntology":null},{"paper":"/paper/nsp-bert-a-prompt-based-zero-shot-learner","slug":"nsp-bert-a-prompt-based-zero-shot-learner","title":"NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction","date":"2021-09-08","arxiv_id":"2109.03564","n_code_links":1,"syntology":null},{"paper":"/paper/panoptic-segformer","slug":"panoptic-segformer","title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","date":"2021-09-08","arxiv_id":"2109.03814","n_code_links":3,"syntology":null},{"paper":null,"slug":"retrieve-caption-generate-visual-grounding","title":"Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models","date":"2021-09-08","arxiv_id":"2109.03892","n_code_links":0,"syntology":null},{"paper":null,"slug":"sustainable-modular-debiasing-of-language","title":"Sustainable Modular Debiasing of Language Models","date":"2021-09-08","arxiv_id":"2109.03646","n_code_links":0,"syntology":null},{"paper":"/paper/truthfulqa-measuring-how-models-mimic-human","slug":"truthfulqa-measuring-how-models-mimic-human","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","date":"2021-09-08","arxiv_id":"2109.07958","n_code_links":3,"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":["sylinrl/truthfulqa"],"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/what-s-hidden-in-a-one-layer-randomly","slug":"what-s-hidden-in-a-one-layer-randomly","title":"What's Hidden in a One-layer Randomly Weighted Transformer?","date":"2021-09-08","arxiv_id":"2109.03939","n_code_links":1,"syntology":null},{"paper":null,"slug":"which-and-where-to-focus-a-simple-yet","title":"Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images","date":"2021-09-08","arxiv_id":"2109.03451","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-classification-system-for","title":"BERT based classification system for detecting rumours on Twitter","date":"2021-09-07","arxiv_id":"2109.02975","n_code_links":0,"syntology":null},{"paper":null,"slug":"empathetic-dialogue-generation-with-pre","title":"Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge","date":"2021-09-07","arxiv_id":"2109.03004","n_code_links":0,"syntology":null},{"paper":"/paper/fhac-at-germeval-2021-identifying-german","slug":"fhac-at-germeval-2021-identifying-german","title":"FHAC at GermEval 2021: Identifying German toxic, engaging, and fact-claiming comments with ensemble learning","date":"2021-09-07","arxiv_id":"2109.03094","n_code_links":1,"syntology":null},{"paper":"/paper/fuseformer-fusing-fine-grained-information-in","slug":"fuseformer-fusing-fine-grained-information-in","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","date":"2021-09-07","arxiv_id":"2109.02974","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":11,"phrase":"10 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ruiliu-ai/fuseformer"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":8,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gcst-graph-convolutional-skeleton-transformer","title":"Hierarchical Graph Convolutional Skeleton Transformer for Action Recognition","date":"2021-09-07","arxiv_id":"2109.02860","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-much-pretraining-data-do-language-models","title":"How much pretraining data do language models need to learn syntax?","date":"2021-09-07","arxiv_id":"2109.03160","n_code_links":0,"syntology":null},{"paper":"/paper/memory-based-semantic-parsing","slug":"memory-based-semantic-parsing","title":"Memory-Based Semantic Parsing","date":"2021-09-07","arxiv_id":"2110.07358","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixed-attention-transformer-for","title":"Mixed Attention Transformer for Leveraging Word-Level Knowledge to Neural Cross-Lingual Information Retrieval","date":"2021-09-07","arxiv_id":"2109.02789","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-branch-deep-radial-basis-function","title":"Multi-Branch Deep Radial Basis Function Networks for Facial Emotion Recognition","date":"2021-09-07","arxiv_id":"2109.03336","n_code_links":0,"syntology":null},{"paper":null,"slug":"naturalness-evaluation-of-natural-language","title":"Naturalness Evaluation of Natural Language Generation in Task-oriented Dialogues using BERT","date":"2021-09-07","arxiv_id":"2109.02938","n_code_links":0,"syntology":null},{"paper":"/paper/nnformer-interleaved-transformer-for","slug":"nnformer-interleaved-transformer-for","title":"nnFormer: Interleaved Transformer for Volumetric Segmentation","date":"2021-09-07","arxiv_id":"2109.03201","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":["282857341/nnformer"],"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":"numgpt-improving-numeracy-ability-of","title":"NumGPT: Improving Numeracy Ability of Generative Pre-trained Models","date":"2021-09-07","arxiv_id":"2109.03137","n_code_links":0,"syntology":null},{"paper":"/paper/pause-positive-and-annealed-unlabeled","slug":"pause-positive-and-annealed-unlabeled","title":"PAUSE: Positive and Annealed Unlabeled Sentence Embedding","date":"2021-09-07","arxiv_id":"2109.03155","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":["eqtpartners/pause"],"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":null,"slug":"puzzle-solving-without-search-or-human","title":"Puzzle Solving without Search or Human Knowledge: An Unnatural Language Approach","date":"2021-09-07","arxiv_id":"2109.02797","n_code_links":0,"syntology":null},{"paper":"/paper/refining-bert-embeddings-for-document-hashing","slug":"refining-bert-embeddings-for-document-hashing","title":"Refining BERT Embeddings for Document Hashing via Mutual Information Maximization","date":"2021-09-07","arxiv_id":"2109.02867","n_code_links":1,"syntology":null},{"paper":"/paper/rendezvous-attention-mechanisms-for-the","slug":"rendezvous-attention-mechanisms-for-the","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","date":"2021-09-07","arxiv_id":"2109.03223","n_code_links":8,"syntology":null},{"paper":"/paper/text-free-prosody-aware-generative-spoken","slug":"text-free-prosody-aware-generative-spoken","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","date":"2021-09-07","arxiv_id":"2109.03264","n_code_links":1,"syntology":null},{"paper":"/paper/3d-human-texture-estimation-from-a-single","slug":"3d-human-texture-estimation-from-a-single","title":"3D Human Texture Estimation from a Single Image with Transformers","date":"2021-09-06","arxiv_id":"2109.02563","n_code_links":1,"syntology":{"ran":14,"of":16,"n_ran_checked":7,"n_instrument":7,"unverified":2,"pointer_only":16,"phrase":"14 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","official":{"repos":["xuxy09/texformer"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/does-bert-learn-as-humans-perceive","slug":"does-bert-learn-as-humans-perceive","title":"Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica","date":"2021-09-06","arxiv_id":"2109.02738","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["sweetpeach/hummingbird"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/eliminating-sentiment-bias-for-aspect-level","slug":"eliminating-sentiment-bias-for-aspect-level","title":"Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction","date":"2021-09-06","arxiv_id":"2109.02403","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-language-models-with-plug-and-play","slug":"enhancing-language-models-with-plug-and-play","title":"Enhancing Natural Language Representation with Large-Scale Out-of-Domain Commonsense","date":"2021-09-06","arxiv_id":"2109.02572","n_code_links":1,"syntology":null},{"paper":"/paper/general-purpose-question-answering-with-macaw","slug":"general-purpose-question-answering-with-macaw","title":"General-Purpose Question-Answering with Macaw","date":"2021-09-06","arxiv_id":"2109.02593","n_code_links":2,"syntology":null},{"paper":"/paper/gpt-3-models-are-poor-few-shot-learners-in","slug":"gpt-3-models-are-poor-few-shot-learners-in","title":"GPT-3 Models are Poor Few-Shot Learners in the Biomedical Domain","date":"2021-09-06","arxiv_id":"2109.02555","n_code_links":1,"syntology":null},{"paper":"/paper/permuteformer-efficient-relative-position","slug":"permuteformer-efficient-relative-position","title":"PermuteFormer: Efficient Relative Position Encoding for Long Sequences","date":"2021-09-06","arxiv_id":"2109.02377","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","official":{"repos":["cpcp1998/permuteformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ss-bert-mitigating-identity-terms-bias-in","title":"SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of \"Subjectivity\" and \"Identity Terms\"","date":"2021-09-06","arxiv_id":"2109.02691","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-animation-transformer-visual","title":"The Animation Transformer: Visual Correspondence via Segment Matching","date":"2021-09-06","arxiv_id":"2109.02614","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformers-for-weeds-and-crops","title":"Vision Transformers For Weeds and Crops Classification Of High Resolution UAV Images","date":"2021-09-06","arxiv_id":"2109.02716","n_code_links":0,"syntology":null},{"paper":"/paper/voxel-transformer-for-3d-object-detection","slug":"voxel-transformer-for-3d-object-detection","title":"Voxel Transformer for 3D Object Detection","date":"2021-09-06","arxiv_id":"2109.02497","n_code_links":1,"syntology":{"ran":0,"of":7,"n_ran_checked":0,"n_instrument":0,"unverified":7,"pointer_only":7,"phrase":"0 ran · 7 unverified","official":null}},{"paper":"/paper/identification-of-driver-phone-usage","slug":"identification-of-driver-phone-usage","title":"Identification of Driver Phone Usage Violations via State-of-the-Art Object Detection with Tracking","date":"2021-09-05","arxiv_id":"2109.02119","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-models-for-text-coherence","slug":"transformer-models-for-text-coherence","title":"Transformer Models for Text Coherence Assessment","date":"2021-09-05","arxiv_id":"2109.02176","n_code_links":2,"syntology":null},{"paper":null,"slug":"error-detection-in-large-scale-natural","title":"Error Detection in Large-Scale Natural Language Understanding Systems Using Transformer Models","date":"2021-09-04","arxiv_id":"2109.01754","n_code_links":0,"syntology":null},{"paper":null,"slug":"real-world-adversarial-examples-involving","title":"Real-World Adversarial Examples involving Makeup Application","date":"2021-09-04","arxiv_id":"2109.03329","n_code_links":0,"syntology":null},{"paper":"/paper/uncovering-the-limits-of-text-based-emotion","slug":"uncovering-the-limits-of-text-based-emotion","title":"Uncovering the Limits of Text-based Emotion Detection","date":"2021-09-04","arxiv_id":"2109.01900","n_code_links":2,"syntology":null},{"paper":"/paper/a-context-aware-hierarchical-bert-fusion","slug":"a-context-aware-hierarchical-bert-fusion","title":"A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection","date":"2021-09-03","arxiv_id":"2109.01267","n_code_links":1,"syntology":null},{"paper":"/paper/automated-detection-of-covid-19-cases-from","slug":"automated-detection-of-covid-19-cases-from","title":"Automated detection of COVID-19 cases from chest X-ray images using deep neural network and XGBoost","date":"2021-09-03","arxiv_id":"2109.02428","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextualized-embeddings-based-convolutional","title":"Contextualized Embeddings based Convolutional Neural Networks for Duplicate Question Identification","date":"2021-09-03","arxiv_id":"2109.01560","n_code_links":0,"syntology":null},{"paper":null,"slug":"early-detection-of-retinopathy-of-prematurity-1","title":"Early Detection of Retinopathy of Prematurity stage using Deep Learning approach","date":"2021-09-03","arxiv_id":"2109.01442","n_code_links":0,"syntology":null},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","n_code_links":8,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["google-research/flan"],"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":"img2smi-translating-molecular-structure","title":"IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System","date":"2021-09-03","arxiv_id":"2109.04202","n_code_links":0,"syntology":null},{"paper":null,"slug":"no-need-to-know-everything-efficiently","title":"No Need to Know Everything! Efficiently Augmenting Language Models With External Knowledge","date":"2021-09-03","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-segmentation-on-vspw-dataset-through","title":"Semantic Segmentation on VSPW Dataset through Aggregation of Transformer Models","date":"2021-09-03","arxiv_id":"2109.01316","n_code_links":0,"syntology":null},{"paper":"/paper/codet5-identifier-aware-unified-pre-trained","slug":"codet5-identifier-aware-unified-pre-trained","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","date":"2021-09-02","arxiv_id":"2109.00859","n_code_links":5,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["salesforce/codet5"],"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":null,"slug":"conqx-semantic-expansion-of-spoken-queries","title":"ConQX: Semantic Expansion of Spoken Queries for Intent Detection based on Conditioned Text Generation","date":"2021-09-02","arxiv_id":"2109.00729","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-based-mitosis-detection-in","title":"Deep Learning-based mitosis detection in breast cancer histologic samples","date":"2021-09-02","arxiv_id":"2109.00816","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-single-shot-multibox-detector","title":"Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse","date":"2021-09-02","arxiv_id":"2109.00810","n_code_links":0,"syntology":null},{"paper":null,"slug":"legalmfit-efficient-short-legal-text","title":"LegaLMFiT: Efficient Short Legal Text Classification with LSTM Language Model Pre-Training","date":"2021-09-02","arxiv_id":"2109.00993","n_code_links":0,"syntology":null},{"paper":null,"slug":"so-cloze-yet-so-far-n400-amplitude-is-better","title":"So Cloze yet so Far: N400 Amplitude is Better Predicted by Distributional Information than Human Predictability Judgements","date":"2021-09-02","arxiv_id":"2109.01226","n_code_links":0,"syntology":null},{"paper":null,"slug":"travelbert-pre-training-language-model","title":"Pre-training Language Model Incorporating Domain-specific Heterogeneous Knowledge into A Unified Representation","date":"2021-09-02","arxiv_id":"2109.01048","n_code_links":0,"syntology":null},{"paper":"/paper/common-objects-in-3d-large-scale-learning-and","slug":"common-objects-in-3d-large-scale-learning-and","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","date":"2021-09-01","arxiv_id":"2109.00512","n_code_links":1,"syntology":null},{"paper":"/paper/ctal-pre-training-cross-modal-transformer-for","slug":"ctal-pre-training-cross-modal-transformer-for","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","date":"2021-09-01","arxiv_id":"2109.00181","n_code_links":1,"syntology":{"ran":15,"of":19,"n_ran_checked":15,"n_instrument":0,"unverified":4,"pointer_only":6,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ydkwim/ctal"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/dilbert-customized-pre-training-for-domain","slug":"dilbert-customized-pre-training-for-domain","title":"DILBERT: Customized Pre-Training for Domain Adaptation withCategory Shift, with an Application to Aspect Extraction","date":"2021-09-01","arxiv_id":"2109.00571","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-person-search-an-anchor-free","slug":"efficient-person-search-an-anchor-free","title":"Efficient Person Search: An Anchor-Free Approach","date":"2021-09-01","arxiv_id":"2109.00211","n_code_links":4,"syntology":null},{"paper":"/paper/exploring-deep-learning-methods-for","slug":"exploring-deep-learning-methods-for","title":"Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts","date":"2021-09-01","arxiv_id":"2109.00343","n_code_links":2,"syntology":null},{"paper":null,"slug":"fight-fire-with-fire-fine-tuning-hate","title":"Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech","date":"2021-09-01","arxiv_id":"2109.00591","n_code_links":0,"syntology":null},{"paper":"/paper/infty-former-infinite-memory-transformer","slug":"infty-former-infinite-memory-transformer","title":"$\\infty$-former: Infinite Memory Transformer","date":"2021-09-01","arxiv_id":"2109.00301","n_code_links":1,"syntology":null},{"paper":"/paper/optagan-entropy-based-finetuning-on-text-vae","slug":"optagan-entropy-based-finetuning-on-text-vae","title":"OptAGAN: Entropy-based finetuning on text VAE-GAN","date":"2021-09-01","arxiv_id":"2109.00239","n_code_links":1,"syntology":null},{"paper":"/paper/searching-for-efficient-multi-stage-vision","slug":"searching-for-efficient-multi-stage-vision","title":"Searching for Efficient Multi-Stage Vision Transformers","date":"2021-09-01","arxiv_id":"2109.00642","n_code_links":1,"syntology":null},{"paper":"/paper/stochastic-transformer-networks-with-linear","slug":"stochastic-transformer-networks-with-linear","title":"Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation","date":"2021-09-01","arxiv_id":"2109.13318","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["avoskou/Stochastic-Transformer-Networks-with-Linear-Competing-Units-Application-to-end-to-end-SL-Translatio"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-improving-adversarial-training-of-nlp","slug":"towards-improving-adversarial-training-of-nlp","title":"Towards Improving Adversarial Training of NLP Models","date":"2021-09-01","arxiv_id":"2109.00544","n_code_links":1,"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":["QData/TextAttack-A2T"],"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":"/paper/arat5-text-to-text-transformers-for-arabic","slug":"arat5-text-to-text-transformers-for-arabic","title":"AraT5: Text-to-Text Transformers for Arabic Language Generation","date":"2021-08-31","arxiv_id":"2109.12068","n_code_links":1,"syntology":null},{"paper":"/paper/automated-mining-of-leaderboards-for","slug":"automated-mining-of-leaderboards-for","title":"Automated Mining of Leaderboards for Empirical AI Research","date":"2021-08-31","arxiv_id":"2109.13089","n_code_links":1,"syntology":null},{"paper":null,"slug":"chi-square-loss-for-softmax-an-echo-of-neural","title":"Chi-square Loss for Softmax: an Echo of Neural Network Structure","date":"2021-08-31","arxiv_id":"2108.13822","n_code_links":0,"syntology":null},{"paper":null,"slug":"effectiveness-of-deep-networks-in-nlp-using","title":"Effectiveness of Deep Networks in NLP using BiDAF as an example architecture","date":"2021-08-31","arxiv_id":"2109.00074","n_code_links":0,"syntology":null},{"paper":"/paper/enjoy-the-salience-towards-better-transformer","slug":"enjoy-the-salience-towards-better-transformer","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","date":"2021-08-31","arxiv_id":"2108.13759","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-does-adversarial-fine-tuning-benefit-bert","title":"How Does Adversarial Fine-Tuning Benefit BERT?","date":"2021-08-31","arxiv_id":"2108.13602","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-sansformers-training-self-supervised","title":"SANSformers: Self-Supervised Forecasting in Electronic Health Records with Attention-Free Models","date":"2021-08-31","arxiv_id":"2108.13672","n_code_links":0,"syntology":null},{"paper":"/paper/minif2f-a-cross-system-benchmark-for-formal","slug":"minif2f-a-cross-system-benchmark-for-formal","title":"MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics","date":"2021-08-31","arxiv_id":"2109.00110","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openai/minif2f"],"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":"monolingual-versus-multilingual-bertology-for","title":"Monolingual versus Multilingual BERTology for Vietnamese Extractive Multi-Document Summarization","date":"2021-08-31","arxiv_id":"2108.13741","n_code_links":0,"syntology":null}],"record_sha256":"1f2fd904411c5490f236d5da70dd8cb29ff189d1970cb3be0958e5f251fdbfaf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}