{"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/320","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":320,"pages_in_order":375,"rows_per_page":100,"rows":[31901,32000],"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/319","next":"/method/softmax/papers/321","papers":[{"paper":"/paper/coder-knowledge-infused-cross-lingual-medical","slug":"coder-knowledge-infused-cross-lingual-medical","title":"CODER: Knowledge infused cross-lingual medical term embedding for term normalization","date":"2020-11-05","arxiv_id":"2011.02947","n_code_links":1,"syntology":null},{"paper":null,"slug":"competence-level-prediction-and-resume-job","title":"Competence-Level Prediction and Resume & Job Description Matching Using Context-Aware Transformer Models","date":"2020-11-05","arxiv_id":"2011.02998","n_code_links":0,"syntology":null},{"paper":"/paper/deep-dup-an-adversarial-weight-duplication","slug":"deep-dup-an-adversarial-weight-duplication","title":"Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA","date":"2020-11-05","arxiv_id":"2011.03006","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-deep-learning-methods-for","slug":"end-to-end-deep-learning-methods-for","title":"End-to-end Deep Learning Methods for Automated Damage Detection in Extreme Events at Various Scales","date":"2020-11-05","arxiv_id":"2011.03098","n_code_links":0,"syntology":null},{"paper":"/paper/nuaa-qmul-at-semeval-2020-task-8-utilizing","slug":"nuaa-qmul-at-semeval-2020-task-8-utilizing","title":"NUAA-QMUL at SemEval-2020 Task 8: Utilizing BERT and DenseNet for Internet Meme Emotion Analysis","date":"2020-11-05","arxiv_id":"2011.02788","n_code_links":1,"syntology":null},{"paper":"/paper/indic-transformers-an-analysis-of-transformer","slug":"indic-transformers-an-analysis-of-transformer","title":"Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages","date":"2020-11-04","arxiv_id":"2011.02323","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-novel-verb-learning-in-bert","slug":"investigating-novel-verb-learning-in-bert","title":"Investigating Novel Verb Learning in BERT: Selectional Preference Classes and Alternation-Based Syntactic Generalization","date":"2020-11-04","arxiv_id":"2011.02417","n_code_links":1,"syntology":null},{"paper":"/paper/lightweight-model-for-the-prediction-of-covid","slug":"lightweight-model-for-the-prediction-of-covid","title":"Lightweight Model For The Prediction of COVID-19 Through The Detection And Segmentation of Lesions in Chest CT Scans","date":"2020-11-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/mtlb-struct-parseme-2020-capturing-unseen","slug":"mtlb-struct-parseme-2020-capturing-unseen","title":"MTLB-STRUCT @PARSEME 2020: Capturing Unseen Multiword Expressions Using Multi-task Learning and Pre-trained Masked Language Models","date":"2020-11-04","arxiv_id":"2011.02541","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-transformer-for-low-resource","title":"Optimizing Transformer for Low-Resource Neural Machine Translation","date":"2020-11-04","arxiv_id":"2011.02266","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-multilingual-bert-for-genetic-and","title":"Probing Multilingual BERT for Genetic and Typological Signals","date":"2020-11-04","arxiv_id":"2011.02070","n_code_links":0,"syntology":null},{"paper":null,"slug":"prosodic-representation-learning-and","title":"Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech","date":"2020-11-04","arxiv_id":"2011.02252","n_code_links":0,"syntology":null},{"paper":null,"slug":"sd-measure-a-social-distancing-detector","title":"SD-Measure: A Social Distancing Detector","date":"2020-11-04","arxiv_id":"2011.02365","n_code_links":0,"syntology":null},{"paper":"/paper/bionerflair-biomedical-named-entity","slug":"bionerflair-biomedical-named-entity","title":"BioNerFlair: biomedical named entity recognition using flair embedding and sequence tagger","date":"2020-11-03","arxiv_id":"2011.01504","n_code_links":1,"syntology":null},{"paper":"/paper/charbert-character-aware-pre-trained-language","slug":"charbert-character-aware-pre-trained-language","title":"CharBERT: Character-aware Pre-trained Language Model","date":"2020-11-03","arxiv_id":"2011.01513","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":8,"n_instrument":2,"unverified":3,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["wtma/CharBERT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/cross-media-keyphrase-prediction-a-unified","slug":"cross-media-keyphrase-prediction-a-unified","title":"Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings","date":"2020-11-03","arxiv_id":"2011.01565","n_code_links":1,"syntology":null},{"paper":"/paper/finding-friends-and-flipping-frenemies","slug":"finding-friends-and-flipping-frenemies","title":"Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory","date":"2020-11-03","arxiv_id":"2011.01856","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"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) · 1 unverified","official":{"repos":["hannahxchen/automatic-paraphrase-dataset-augmentation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generating-synthetic-data-for-task-oriented","title":"Generating Synthetic Data for Task-Oriented Semantic Parsing with Hierarchical Representations","date":"2020-11-03","arxiv_id":"2011.02050","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-rnn-transducer-with-normalized","title":"Improving RNN transducer with normalized jointer network","date":"2020-11-03","arxiv_id":"2011.01576","n_code_links":0,"syntology":null},{"paper":"/paper/in-defense-of-feature-mimicking-for-knowledge","slug":"in-defense-of-feature-mimicking-for-knowledge","title":"Distilling Knowledge by Mimicking Features","date":"2020-11-03","arxiv_id":"2011.01424","n_code_links":3,"syntology":{"ran":5,"of":6,"n_ran_checked":1,"n_instrument":4,"unverified":1,"pointer_only":6,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["DoctorKey/LSHFM.detection","DoctorKey/LSHFM.multiclassification","DoctorKey/LSHFM.singleclassification"],"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","unlocated"]}}},{"paper":null,"slug":"out-of-distribution-detection-for-automotive","title":"Out-of-Distribution Detection for Automotive Perception","date":"2020-11-03","arxiv_id":"2011.01413","n_code_links":0,"syntology":null},{"paper":"/paper/sound-natural-content-rephrasing-in-dialog","slug":"sound-natural-content-rephrasing-in-dialog","title":"Sound Natural: Content Rephrasing in Dialog Systems","date":"2020-11-03","arxiv_id":"2011.01993","n_code_links":1,"syntology":null},{"paper":"/paper/tabular-transformers-for-modeling","slug":"tabular-transformers-for-modeling","title":"Tabular Transformers for Modeling Multivariate Time Series","date":"2020-11-03","arxiv_id":"2011.01843","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["IBM/TabFormer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/xed-a-multilingual-dataset-for-sentiment","slug":"xed-a-multilingual-dataset-for-sentiment","title":"XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection","date":"2020-11-03","arxiv_id":"2011.01612","n_code_links":1,"syntology":null},{"paper":"/paper/a-closer-look-at-linguistic-knowledge-in","slug":"a-closer-look-at-linguistic-knowledge-in","title":"A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English","date":"2020-11-02","arxiv_id":"2011.00960","n_code_links":1,"syntology":null},{"paper":"/paper/abnirml-analyzing-the-behavior-of-neural-ir","slug":"abnirml-analyzing-the-behavior-of-neural-ir","title":"ABNIRML: Analyzing the Behavior of Neural IR Models","date":"2020-11-02","arxiv_id":"2011.00696","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/abnirml"],"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":["official"]}}},{"paper":null,"slug":"abstracting-influence-paths-for-explaining-1","title":"Influence Patterns for Explaining Information Flow in BERT","date":"2020-11-02","arxiv_id":"2011.00740","n_code_links":0,"syntology":null},{"paper":null,"slug":"cabinet-efficient-context-aggregation-network","title":"Real-time Semantic Segmentation with Context Aggregation Network","date":"2020-11-02","arxiv_id":"2011.00993","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-representation-decomposition-for-feature","title":"Representation Decomposition for Image Manipulation and Beyond","date":"2020-11-02","arxiv_id":"2011.00788","n_code_links":0,"syntology":null},{"paper":"/paper/dual-decoder-transformer-for-joint-automatic","slug":"dual-decoder-transformer-for-joint-automatic","title":"Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation","date":"2020-11-02","arxiv_id":"2011.00747","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-far-does-bert-look-at-distance-based","title":"How Far Does BERT Look At:Distance-based Clustering and Analysis of BERT$'$s Attention","date":"2020-11-02","arxiv_id":"2011.00943","n_code_links":0,"syntology":null},{"paper":"/paper/introducing-various-semantic-models-for","slug":"introducing-various-semantic-models-for","title":"Introducing various Semantic Models for Amharic: Experimentation and Evaluation with multiple Tasks and Datasets","date":"2020-11-02","arxiv_id":"2011.01154","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-sentence-embeddings-from-pre-trained","slug":"on-the-sentence-embeddings-from-pre-trained","title":"On the Sentence Embeddings from Pre-trained Language Models","date":"2020-11-02","arxiv_id":"2011.05864","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bohanli/BERT-flow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/point-transformer","slug":"point-transformer","title":"Point Transformer","date":"2020-11-02","arxiv_id":"2011.00931","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["engelnico/point-transformer"],"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":["listed","official"]}}},{"paper":null,"slug":"qmul-sds-at-sardistance2020-leveraging","title":"QMUL-SDS @ SardiStance: Leveraging Network Interactions to Boost Performance on Stance Detection using Knowledge Graphs","date":"2020-11-02","arxiv_id":"2011.01181","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-federated-learning-for","title":"Semi-supervised Federated Learning for Activity Recognition","date":"2020-11-02","arxiv_id":"2011.00851","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-pointer-network-architecture-for-joint","title":"A Pointer Network Architecture for Joint Morphological Segmentation and Tagging","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-semantics-based-approach-to-disclosure","title":"A Semantics-based Approach to Disclosure Classification in User-Generated Online Content","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-structure-enhanced-graph-convolutional","title":"A structure-enhanced graph convolutional network for sentiment analysis","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"active-learning-approaches-to-enhancing","title":"Active Learning Approaches to Enhancing Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/analysing-word-representation-from-the-input","slug":"analysing-word-representation-from-the-input","title":"Analysing Word Representation from the Input and Output Embeddings in Neural Network Language Models","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/approximation-of-response-knowledge-retrieval","slug":"approximation-of-response-knowledge-retrieval","title":"Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/chime-cross-passage-hierarchical-memory","slug":"chime-cross-passage-hierarchical-memory","title":"CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering","date":"2020-11-01","arxiv_id":"2011.00519","n_code_links":1,"syntology":null},{"paper":"/paper/conceptbert-concept-aware-representation-for","slug":"conceptbert-concept-aware-representation-for","title":"ConceptBert: Concept-Aware Representation for Visual Question Answering","date":"2020-11-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"context-analysis-for-pre-trained-masked","title":"Context Analysis for Pre-trained Masked Language Models","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/coot-cooperative-hierarchical-transformer-for","slug":"coot-cooperative-hierarchical-transformer-for","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","date":"2020-11-01","arxiv_id":"2011.00597","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gingsi/coot-videotext"],"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":["official"]}}},{"paper":null,"slug":"cross-lingual-training-of-neural-models-for","title":"Cross-Lingual Training of Neural Models for Document Ranking","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/decoding-language-spatial-relations-to-2d","slug":"decoding-language-spatial-relations-to-2d","title":"Decoding Language Spatial Relations to 2D Spatial Arrangements","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/deep-diacritization-efficient-hierarchical","slug":"deep-diacritization-efficient-hierarchical","title":"Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization","date":"2020-11-01","arxiv_id":"2011.00538","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamically-throttleable-neural-networks-tnn","title":"Dynamically Throttleable Neural Networks (TNN)","date":"2020-11-01","arxiv_id":"2011.02836","n_code_links":0,"syntology":null},{"paper":"/paper/enhance-robustness-of-sequence-labelling-with","slug":"enhance-robustness-of-sequence-labelling-with","title":"Enhance Robustness of Sequence Labelling with Masked Adversarial Training","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-generalization-in-natural-language","slug":"enhancing-generalization-in-natural-language","title":"Enhancing Generalization in Natural Language Inference by Syntax","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"exbert-extending-pre-trained-models-with","title":"exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"factorized-transformer-for-multi-domain","title":"Factorized Transformer for Multi-Domain Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-speech-and-offensive-language-detection","title":"Hate-Speech and Offensive Language Detection in Roman Urdu","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"huji-ku-at-mrp-2020-two-transition-based-1","title":"HUJI-KU at MRP 2020: Two Transition-based Neural Parsers","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/integrating-task-specific-information-into","slug":"integrating-task-specific-information-into","title":"Integrating Task Specific Information into Pretrained Language Models for Low Resource Fine Tuning","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"investigation-of-bert-model-on-biomedical","title":"Investigation of BERT Model on Biomedical Relation Extraction Based on Revised Fine-tuning Mechanism","date":"2020-11-01","arxiv_id":"2011.00398","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-ground-medical-text-in-a-3d-human","slug":"learning-to-ground-medical-text-in-a-3d-human","title":"Learning to ground medical text in a 3D human atlas","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/limit-bert-linguistics-informed-multi-task","slug":"limit-bert-linguistics-informed-multi-task","title":"LIMIT-BERT : Linguistics Informed Multi-Task BERT","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"making-information-seeking-easier-an-improved","title":"Making Information Seeking Easier: An Improved Pipeline for Conversational Search","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-intra-and-inter-modality-incongruity","title":"Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-2oie-multilingual-open-information-1","slug":"multi-2oie-multilingual-open-information-1","title":"Multi\\^2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-word-segmentation-for-downstream","slug":"optimizing-word-segmentation-for-downstream","title":"Optimizing Word Segmentation for Downstream Task","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-responses-to-psychological","title":"Predicting Responses to Psychological Questionnaires from Participants' Social Media Posts and Question Text Embeddings","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/representation-learning-for-type-driven","slug":"representation-learning-for-type-driven","title":"Representation Learning for Type-Driven Composition","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/seeing-both-the-forest-and-the-trees-multi","slug":"seeing-both-the-forest-and-the-trees-multi","title":"Seeing Both the Forest and the Trees: Multi-head Attention for Joint Classification on Different Compositional Levels","date":"2020-11-01","arxiv_id":"2011.00470","n_code_links":1,"syntology":null},{"paper":null,"slug":"smrt-chatbots-improving-non-task-oriented","title":"SMRT Chatbots: Improving Non-Task-Oriented Dialog with Simulated Multiple Reference Training","date":"2020-11-01","arxiv_id":"2011.00547","n_code_links":0,"syntology":null},{"paper":"/paper/social-chemistry-101-learning-to-reason-about","slug":"social-chemistry-101-learning-to-reason-about","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","date":"2020-11-01","arxiv_id":"2011.00620","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-amazing-world-of-neural-language","title":"The Amazing World of Neural Language Generation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/the-relx-dataset-and-matching-the-1","slug":"the-relx-dataset-and-matching-the-1","title":"The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/towards-zero-shot-conditional-summarization","slug":"towards-zero-shot-conditional-summarization","title":"Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-multi-aspect-modeling-for","title":"Transformer-based Multi-Aspect Modeling for Multi-Aspect Multi-Sentiment Analysis","date":"2020-11-01","arxiv_id":"2011.00476","n_code_links":0,"syntology":null},{"paper":"/paper/visually-grounded-planning-without-vision-1","slug":"visually-grounded-planning-without-vision-1","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/efficient-arabic-emotion-recognition-using","slug":"efficient-arabic-emotion-recognition-using","title":"Efficient Arabic emotion recognition using deep neural networks","date":"2020-10-31","arxiv_id":"2011.00346","n_code_links":1,"syntology":null},{"paper":"/paper/free-the-plural-unrestricted-split-antecedent","slug":"free-the-plural-unrestricted-split-antecedent","title":"Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution","date":"2020-10-31","arxiv_id":"2011.00245","n_code_links":1,"syntology":null},{"paper":null,"slug":"methods-for-pruning-deep-neural-networks","title":"Methods for Pruning Deep Neural Networks","date":"2020-10-31","arxiv_id":"2011.00241","n_code_links":0,"syntology":null},{"paper":"/paper/neural-coreference-resolution-for-arabic","slug":"neural-coreference-resolution-for-arabic","title":"Neural Coreference Resolution for Arabic","date":"2020-10-31","arxiv_id":"2011.00286","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-xx205-system-for-the-voxceleb-speaker","title":"The xx205 System for the VoxCeleb Speaker Recognition Challenge 2020","date":"2020-10-31","arxiv_id":"2011.00200","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-pre-trained-bert-for-aspect","slug":"understanding-pre-trained-bert-for-aspect","title":"Understanding Pre-trained BERT for Aspect-based Sentiment Analysis","date":"2020-10-31","arxiv_id":"2011.00169","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-sui-generis-qa-approach-using-roberta-for","title":"A Sui Generis QA Approach using RoBERTa for Adverse Drug Event Identification","date":"2020-10-30","arxiv_id":"2011.00057","n_code_links":0,"syntology":null},{"paper":"/paper/generating-radiology-reports-via-memory","slug":"generating-radiology-reports-via-memory","title":"Generating Radiology Reports via Memory-driven Transformer","date":"2020-10-30","arxiv_id":"2010.16056","n_code_links":2,"syntology":{"ran":26,"of":31,"n_ran_checked":20,"n_instrument":6,"unverified":5,"pointer_only":25,"phrase":"26 ran (of which 13 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 3 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","official":{"repos":["zhjohnchan/R2Gen"],"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":["found_in_text","listed","official"]}}},{"paper":null,"slug":"improving-dialogue-breakdown-detection-with","title":"Improving Dialogue Breakdown Detection with Semi-Supervised Learning","date":"2020-10-30","arxiv_id":"2011.00136","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-labeling-using-a-deep-contextualized","slug":"semantic-labeling-using-a-deep-contextualized","title":"Semantic Labeling Using a Deep Contextualized Language Model","date":"2020-10-30","arxiv_id":"2010.16037","n_code_links":1,"syntology":null},{"paper":null,"slug":"slm-learning-a-discourse-language","title":"SLM: Learning a Discourse Language Representation with Sentence Unshuffling","date":"2020-10-30","arxiv_id":"2010.16249","n_code_links":0,"syntology":null},{"paper":"/paper/target-word-masking-for-location-metonymy","slug":"target-word-masking-for-location-metonymy","title":"Target Word Masking for Location Metonymy Resolution","date":"2020-10-30","arxiv_id":"2010.16097","n_code_links":1,"syntology":null},{"paper":null,"slug":"topic-preserving-synthetic-news-generation-an","title":"Topic-Preserving Synthetic News Generation: An Adversarial Deep Reinforcement Learning Approach","date":"2020-10-30","arxiv_id":"2010.16324","n_code_links":0,"syntology":null},{"paper":"/paper/veco-variable-encoder-decoder-pre-training-1","slug":"veco-variable-encoder-decoder-pre-training-1","title":"VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation","date":"2020-10-30","arxiv_id":"2010.16046","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-s-in-a-loss-function-for-image","title":"Why Do Better Loss Functions Lead to Less Transferable Features?","date":"2020-10-30","arxiv_id":"2010.16402","n_code_links":0,"syntology":null},{"paper":"/paper/autoprompt-eliciting-knowledge-from-language","slug":"autoprompt-eliciting-knowledge-from-language","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","date":"2020-10-29","arxiv_id":"2010.15980","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["ucinlp/autoprompt"],"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":["listed","official"]}}},{"paper":null,"slug":"black-box-optimization-of-object-detector","title":"Black-Box Optimization of Object Detector Scales","date":"2020-10-29","arxiv_id":"2010.15823","n_code_links":0,"syntology":null},{"paper":"/paper/combining-self-training-and-self-supervised","slug":"combining-self-training-and-self-supervised","title":"Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection","date":"2020-10-29","arxiv_id":"2010.15360","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextual-bert-conditioning-the-language","title":"Contextual BERT: Conditioning the Language Model Using a Global State","date":"2020-10-29","arxiv_id":"2010.15778","n_code_links":0,"syntology":null},{"paper":null,"slug":"memory-attentive-fusion-external-language","title":"Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model","date":"2020-10-29","arxiv_id":"2010.15437","n_code_links":0,"syntology":null},{"paper":"/paper/relationnet-bridging-visual-representations","slug":"relationnet-bridging-visual-representations","title":"RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder","date":"2020-10-29","arxiv_id":"2010.15831","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/RelationNet2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"seq2mol-automatic-design-of-de-novo-molecules","title":"Seq2Mol: Automatic design of de novo molecules conditioned by the target protein sequences through deep neural networks","date":"2020-10-29","arxiv_id":"2010.15900","n_code_links":0,"syntology":null},{"paper":null,"slug":"t-vectors-weakly-supervised-speaker","title":"T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model","date":"2020-10-29","arxiv_id":"2010.16071","n_code_links":0,"syntology":null},{"paper":null,"slug":"tilde-at-wmt-2020-news-task-systems","title":"Tilde at WMT 2020: News Task Systems","date":"2020-10-29","arxiv_id":"2010.15423","n_code_links":0,"syntology":null},{"paper":null,"slug":"accurate-prostate-cancer-detection-and","title":"Accurate Prostate Cancer Detection and Segmentation on Biparametric MRI using Non-local Mask R-CNN with Histopathological Ground Truth","date":"2020-10-28","arxiv_id":"2010.15233","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesian-methods-for-semi-supervised-text","title":"Bayesian Methods for Semi-supervised Text Annotation","date":"2020-10-28","arxiv_id":"2010.14872","n_code_links":0,"syntology":null}],"record_sha256":"1e681048b214976cd50e5e3dd5cff4c864dc79d9c8e279ee64ca1c39bd58e157","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}