{"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/dense-connections/papers/272","list_of":"/method/dense-connections","method":"Dense Connections","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":272,"pages_in_order":293,"rows_per_page":100,"rows":[27101,27200],"of":29230,"counts":{"archive_papers_tagged":29230,"with_a_code_link":12972,"where_syntology_ran_a_sample":3929,"not_listed_spam_title":0,"listed":29230,"listed_where_code_ran":3929,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3303,"every_run_a_failure_of_syntologys_instrument":626,"listed_with_a_run_with_no_instrument_failure":3303,"listed_every_run_a_failure_of_syntologys_instrument":626,"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/dense-connections","prev":"/method/dense-connections/papers/271","next":"/method/dense-connections/papers/273","papers":[{"paper":"/paper/improving-transformer-models-by-reordering","slug":"improving-transformer-models-by-reordering","title":"Improving Transformer Models by Reordering their Sublayers","date":"2019-11-10","arxiv_id":"1911.03864","n_code_links":2,"syntology":null},{"paper":"/paper/inset-sentence-infilling-with-inter","slug":"inset-sentence-infilling-with-inter","title":"INSET: Sentence Infilling with INter-SEntential Transformer","date":"2019-11-10","arxiv_id":"1911.03892","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-few-shot-learn-across-diverse","slug":"learning-to-few-shot-learn-across-diverse","title":"Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks","date":"2019-11-10","arxiv_id":"1911.03863","n_code_links":2,"syntology":null},{"paper":null,"slug":"minimalistic-attacks-how-little-it-takes-to","title":"Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy","date":"2019-11-10","arxiv_id":"1911.03849","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-autoregressive-transformer-automatic","title":"Listen and Fill in the Missing Letters: Non-Autoregressive Transformer for Speech Recognition","date":"2019-11-10","arxiv_id":"1911.04908","n_code_links":0,"syntology":null},{"paper":"/paper/periodic-spectral-ergodicity-a-complexity","slug":"periodic-spectral-ergodicity-a-complexity","title":"Periodic Spectral Ergodicity: A Complexity Measure for Deep Neural Networks and Neural Architecture Search","date":"2019-11-10","arxiv_id":"1911.07831","n_code_links":1,"syntology":null},{"paper":"/paper/rat-sql-relation-aware-schema-encoding-and-1","slug":"rat-sql-relation-aware-schema-encoding-and-1","title":"RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers","date":"2019-11-10","arxiv_id":"1911.04942","n_code_links":4,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Microsoft/rat-sql"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"robust-natural-language-inference-models-with","title":"Increasing Robustness to Spurious Correlations using Forgettable Examples","date":"2019-11-10","arxiv_id":"1911.03861","n_code_links":0,"syntology":null},{"paper":null,"slug":"syntax-infused-transformer-and-bert-models","title":"Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding","date":"2019-11-10","arxiv_id":"1911.06156","n_code_links":0,"syntology":null},{"paper":"/paper/tener-adapting-transformer-encoder-for-name","slug":"tener-adapting-transformer-encoder-for-name","title":"TENER: Adapting Transformer Encoder for Named Entity Recognition","date":"2019-11-10","arxiv_id":"1911.04474","n_code_links":6,"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":["fastnlp/TENER"],"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":"two-headed-monster-and-crossed-co-attention","title":"Two-Headed Monster And Crossed Co-Attention Networks","date":"2019-11-10","arxiv_id":"1911.03897","n_code_links":0,"syntology":null},{"paper":null,"slug":"yelm-end-to-end-contextualized-entity-linking","title":"Contextualized End-to-End Neural Entity Linking","date":"2019-11-10","arxiv_id":"1911.03834","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-entity-linking-with-dense-entity","slug":"zero-shot-entity-linking-with-dense-entity","title":"Scalable Zero-shot Entity Linking with Dense Entity Retrieval","date":"2019-11-10","arxiv_id":"1911.03814","n_code_links":3,"syntology":null},{"paper":"/paper/a-reinforced-generation-of-adversarial","slug":"a-reinforced-generation-of-adversarial","title":"A Reinforced Generation of Adversarial Examples for Neural Machine Translation","date":"2019-11-09","arxiv_id":"1911.03677","n_code_links":1,"syntology":null},{"paper":null,"slug":"attentive-student-meets-multi-task-teacher","title":"MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models","date":"2019-11-09","arxiv_id":"1911.03588","n_code_links":0,"syntology":null},{"paper":"/paper/bert-is-not-a-knowledge-base-yet-factual","slug":"bert-is-not-a-knowledge-base-yet-factual","title":"E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT","date":"2019-11-09","arxiv_id":"1911.03681","n_code_links":1,"syntology":null},{"paper":"/paper/convert-efficient-and-accurate-conversational","slug":"convert-efficient-and-accurate-conversational","title":"ConveRT: Efficient and Accurate Conversational Representations from Transformers","date":"2019-11-09","arxiv_id":"1911.03688","n_code_links":5,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":null}},{"paper":"/paper/deepmask-an-algorithm-for-cloud-and-cloud","slug":"deepmask-an-algorithm-for-cloud-and-cloud","title":"DeepMask: an algorithm for cloud and cloud shadow detection in optical satellite remote sensing images using deep residual network","date":"2019-11-09","arxiv_id":"1911.03607","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-perspective-inferrer-reasoning","title":"Multi-Perspective Inferrer: Reasoning Sentences Relationship from Holistic Perspective","date":"2019-11-09","arxiv_id":"1911.03668","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-dialogue-dodecathlon-open-domain","title":"The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents","date":"2019-11-09","arxiv_id":"1911.03768","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-paraphrase-generation-with","title":"Zero-Shot Paraphrase Generation with Multilingual Language Models","date":"2019-11-09","arxiv_id":"1911.03597","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-relevance-transfer-for-document","title":"Cross-Lingual Relevance Transfer for Document Retrieval","date":"2019-11-08","arxiv_id":"1911.02989","n_code_links":0,"syntology":null},{"paper":"/paper/graph-to-graph-transformer-for-transition","slug":"graph-to-graph-transformer-for-transition","title":"Graph-to-Graph Transformer for Transition-based Dependency Parsing","date":"2019-11-08","arxiv_id":"1911.03561","n_code_links":1,"syntology":null},{"paper":"/paper/how-language-neutral-is-multilingual-bert","slug":"how-language-neutral-is-multilingual-bert","title":"How Language-Neutral is Multilingual BERT?","date":"2019-11-08","arxiv_id":"1911.03310","n_code_links":1,"syntology":null},{"paper":null,"slug":"pretrained-language-models-for-document-level","title":"Pretrained Language Models for Document-Level Neural Machine Translation","date":"2019-11-08","arxiv_id":"1911.03110","n_code_links":0,"syntology":null},{"paper":null,"slug":"question-generation-from-paragraphs-a-tale-of-1","title":"Question Generation from Paragraphs: A Tale of Two Hierarchical Models","date":"2019-11-08","arxiv_id":"1911.03407","n_code_links":0,"syntology":null},{"paper":null,"slug":"resurrecting-submodularity-in-neural","title":"Resurrecting Submodularity for Neural Text Generation","date":"2019-11-08","arxiv_id":"1911.03014","n_code_links":0,"syntology":null},{"paper":null,"slug":"sept-improving-scientific-named-entity","title":"SEPT: Improving Scientific Named Entity Recognition with Span Representation","date":"2019-11-08","arxiv_id":"1911.03353","n_code_links":0,"syntology":null},{"paper":"/paper/towards-hierarchical-importance-attribution-1","slug":"towards-hierarchical-importance-attribution-1","title":"Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models","date":"2019-11-08","arxiv_id":"1911.06194","n_code_links":3,"syntology":null},{"paper":null,"slug":"transforming-wikipedia-into-augmented-data","title":"Transforming Wikipedia into Augmented Data for Query-Focused Summarization","date":"2019-11-08","arxiv_id":"1911.03324","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-would-elsa-do-freezing-layers-during","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","date":"2019-11-08","arxiv_id":"1911.03090","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-deep-transformers-are-difficult-to","title":"Lipschitz Constrained Parameter Initialization for Deep Transformers","date":"2019-11-08","arxiv_id":"1911.03179","n_code_links":0,"syntology":null},{"paper":"/paper/berts-of-a-feather-do-not-generalize-together","slug":"berts-of-a-feather-do-not-generalize-together","title":"BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance","date":"2019-11-07","arxiv_id":"1911.02969","n_code_links":1,"syntology":null},{"paper":"/paper/blockwise-self-attention-for-long-document","slug":"blockwise-self-attention-for-long-document","title":"Blockwise Self-Attention for Long Document Understanding","date":"2019-11-07","arxiv_id":"1911.02972","n_code_links":1,"syntology":null},{"paper":"/paper/conversation-generation-with-concept-flow","slug":"conversation-generation-with-concept-flow","title":"Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs","date":"2019-11-07","arxiv_id":"1911.02707","n_code_links":2,"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: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thunlp/ConceptFlow"],"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":"explicit-pairwise-word-interaction-modeling","title":"Explicit Pairwise Word Interaction Modeling Improves Pretrained Transformers for English Semantic Similarity Tasks","date":"2019-11-07","arxiv_id":"1911.02847","n_code_links":0,"syntology":null},{"paper":"/paper/microsoft-research-asias-systems-for-wmt19-1","slug":"microsoft-research-asias-systems-for-wmt19-1","title":"Microsoft Research Asia's Systems for WMT19","date":"2019-11-07","arxiv_id":"1911.06191","n_code_links":0,"syntology":null},{"paper":null,"slug":"porous-lattice-based-transformer-encoder-for","title":"Porous Lattice-based Transformer Encoder for Chinese NER","date":"2019-11-07","arxiv_id":"1911.02733","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-contextualized-sentence","title":"Probing Contextualized Sentence Representations with Visual Awareness","date":"2019-11-07","arxiv_id":"1911.02971","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-lig-system-for-the-english-czech-text","title":"The LIG system for the English-Czech Text Translation Task of IWSLT 2019","date":"2019-11-07","arxiv_id":"1911.02898","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-dynamic-embeddings-to-improve-static","title":"How Can BERT Help Lexical Semantics Tasks?","date":"2019-11-07","arxiv_id":"1911.02929","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-end-to-end-approach-for-lexical-stress","title":"An End-to-end Approach for Lexical Stress Detection based on Transformer","date":"2019-11-06","arxiv_id":"1911.04862","n_code_links":0,"syntology":null},{"paper":"/paper/coke-contextualized-knowledge-graph-embedding","slug":"coke-contextualized-knowledge-graph-embedding","title":"CoKE: Contextualized Knowledge Graph Embedding","date":"2019-11-06","arxiv_id":"1911.02168","n_code_links":3,"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":["PaddlePaddle/Research","PaddlePaddle/models"],"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":null,"slug":"enriching-conversation-context-in-retrieval","title":"Enriching Conversation Context in Retrieval-based Chatbots","date":"2019-11-06","arxiv_id":"1911.02290","n_code_links":0,"syntology":null},{"paper":"/paper/fast-transformer-decoding-one-write-head-is","slug":"fast-transformer-decoding-one-write-head-is","title":"Fast Transformer Decoding: One Write-Head is All You Need","date":"2019-11-06","arxiv_id":"1911.02150","n_code_links":4,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/graph-transformer-networks-1","slug":"graph-transformer-networks-1","title":"Graph Transformer Networks","date":"2019-11-06","arxiv_id":"1911.06455","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-answer-by-learning-to-ask-getting","title":"Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds","date":"2019-11-06","arxiv_id":"1911.02365","n_code_links":0,"syntology":null},{"paper":null,"slug":"predictive-modeling-of-brain-tumor-a-deep","title":"Predictive modeling of brain tumor: A Deep learning approach","date":"2019-11-06","arxiv_id":"1911.02265","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-domain-adaptation-of-contextual","title":"Unsupervised Domain Adaptation of Contextual Embeddings for Low-Resource Duplicate Question Detection","date":"2019-11-06","arxiv_id":"1911.02645","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-scalable-multilabel-classification-to","title":"A Scalable Multilabel Classification to Deploy Deep Learning Architectures For Edge Devices","date":"2019-11-05","arxiv_id":"1911.02098","n_code_links":0,"syntology":null},{"paper":null,"slug":"deepening-hidden-representations-from-pre","title":"Deepening Hidden Representations from Pre-trained Language Models","date":"2019-11-05","arxiv_id":"1911.01940","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-bidirectional-decoding-with-dynamic","title":"Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation","date":"2019-11-05","arxiv_id":"1911.01597","n_code_links":0,"syntology":null},{"paper":"/paper/improving-slot-filling-by-utilizing","slug":"improving-slot-filling-by-utilizing","title":"Improving Slot Filling by Utilizing Contextual Information","date":"2019-11-05","arxiv_id":"1911.01680","n_code_links":0,"syntology":null},{"paper":null,"slug":"incremental-sense-weight-training-for-the","title":"Incremental Sense Weight Training for the Interpretation of Contextualized Word Embeddings","date":"2019-11-05","arxiv_id":"1911.01623","n_code_links":0,"syntology":null},{"paper":"/paper/mml-maximal-multiverse-learning-for-robust","slug":"mml-maximal-multiverse-learning-for-robust","title":"MML: Maximal Multiverse Learning for Robust Fine-Tuning of Language Models","date":"2019-11-05","arxiv_id":"1911.06182","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-cross-lingual-representation-1","slug":"unsupervised-cross-lingual-representation-1","title":"Unsupervised Cross-lingual Representation Learning at Scale","date":"2019-11-05","arxiv_id":"1911.02116","n_code_links":35,"syntology":{"ran":40,"of":59,"n_ran_checked":35,"n_instrument":5,"unverified":19,"pointer_only":52,"phrase":"40 ran (of which 13 constructed an object rather than computing a result; 35 with no instrument failure: 4 honoured, 1 violated, 30 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified","official":{"repos":["facebookresearch/cc_net","facebookresearch/XLM"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"an-end-to-end-deep-rl-framework-for-task","title":"An End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing Platforms","date":"2019-11-04","arxiv_id":"1911.01030","n_code_links":0,"syntology":null},{"paper":"/paper/assessing-social-and-intersectional-biases-in","slug":"assessing-social-and-intersectional-biases-in","title":"Assessing Social and Intersectional Biases in Contextualized Word Representations","date":"2019-11-04","arxiv_id":"1911.01485","n_code_links":1,"syntology":null},{"paper":null,"slug":"bas-an-answer-selection-method-using-bert","title":"BAS: An Answer Selection Method Using BERT Language Model","date":"2019-11-04","arxiv_id":"1911.01528","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-convolutional-neural-tangent-kernels-1","title":"Enhanced Convolutional Neural Tangent Kernels","date":"2019-11-03","arxiv_id":"1911.00809","n_code_links":0,"syntology":null},{"paper":"/paper/an-algorithm-for-routing-capsules-in-all","slug":"an-algorithm-for-routing-capsules-in-all","title":"An Algorithm for Routing Capsules in All Domains","date":"2019-11-02","arxiv_id":"1911.00792","n_code_links":1,"syntology":null},{"paper":null,"slug":"machine-translation-evaluation-using-bi","title":"Machine Translation Evaluation using Bi-directional Entailment","date":"2019-11-02","arxiv_id":"1911.00681","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentence-level-bert-and-multi-task-learning","title":"Sentence-Level BERT and Multi-Task Learning of Age and Gender in Social Media","date":"2019-11-02","arxiv_id":"1911.00637","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-learning-based-system-for-pharmaconer","title":"A Deep Learning-Based System for PharmaCoNER","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-task-learning-framework-for-2","title":"A Multi-Task Learning Framework for Extracting Bacteria Biotope Information","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-recurrent-bert-based-model-for-question","slug":"a-recurrent-bert-based-model-for-question","title":"A Recurrent BERT-based Model for Question Generation","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"aggregating-bidirectional-encoder","title":"Aggregating Bidirectional Encoder Representations Using MatchLSTM for Sequence Matching","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-bert-to-document-retrieval-with","title":"Applying BERT to Document Retrieval with Birch","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"automatically-extracting-challenge-sets-for-1","title":"Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-goes-to-law-school-quantifying-the","title":"BERT Goes to Law School: Quantifying the Competitive Advantage of Access to Large Legal Corpora in Contract Understanding","date":"2019-11-01","arxiv_id":"1911.00473","n_code_links":0,"syntology":null},{"paper":"/paper/bert-is-not-an-interlingua-and-the-bias-of","slug":"bert-is-not-an-interlingua-and-the-bias-of","title":"BERT is Not an Interlingua and the Bias of Tokenization","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/biomedical-named-entity-recognition-with","slug":"biomedical-named-entity-recognition-with","title":"Biomedical Named Entity Recognition with Multilingual BERT","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"blcu-nlp-at-coin-shared-task1-stagewise-fine","title":"BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"caunlp-at-nlp4if-2019-shared-task-context","title":"CAUnLP at NLP4IF 2019 Shared Task: Context-Dependent BERT for Sentence-Level Propaganda Detection","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cler-cross-task-learning-with-expert","title":"CLER: Cross-task Learning with Expert Representation to Generalize Reading and Understanding","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"comb-convolution-for-efficient-convolutional","title":"Comb Convolution for Efficient Convolutional Architecture","date":"2019-11-01","arxiv_id":"1911.00387","n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-global-sparse-gradients-with-local","title":"Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-unsupervised-pre-training-and","title":"Combining Unsupervised Pre-training and Annotator Rationales to Improve Low-shot Text Classification","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"contextualized-cross-lingual-event-trigger","title":"Contextualized Cross-Lingual Event Trigger Extraction with Minimal Resources","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-sensitive-bert-for-generalisable","title":"Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-domain-modeling-of-sentence-level","title":"Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cvits-submissions-to-wat-2019","title":"CVIT's submissions to WAT-2019","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-bidirectional-transformers-for-relation-1","title":"Deep Bidirectional Transformers for Relation Extraction without Supervision","date":"2019-11-01","arxiv_id":"1911.00313","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-of-propaganda-using-logistic","title":"Detection of Propaganda Using Logistic Regression","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dialect-text-normalization-to-normative","slug":"dialect-text-normalization-to-normative","title":"Dialect Text Normalization to Normative Standard Finnish","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/dialogpt-large-scale-generative-pre-training","slug":"dialogpt-large-scale-generative-pre-training","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","date":"2019-11-01","arxiv_id":"1911.00536","n_code_links":6,"syntology":{"ran":6,"of":12,"n_ran_checked":5,"n_instrument":1,"unverified":6,"pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["microsoft/DialoGPT"],"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":"divisive-language-and-propaganda-detection","title":"Divisive Language and Propaganda Detection using Multi-head Attention Transformers with Deep Learning BERT-based Language Models for Binary Classification","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-adaptation-with-bert-based-domain","title":"Domain Adaptation with BERT-based Domain Classification and Data Selection","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"english-to-hindi-multi-modal-neural-machine","title":"English to Hindi Multi-modal Neural Machine Translation and Hindi Image Captioning","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-transformer-model-for-data-to-text","title":"Enhanced Transformer Model for Data-to-Text Generation","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-bert-for-lexical-normalization","title":"Enhancing BERT for Lexical Normalization","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-bert-for-natural-language","title":"Evaluating BERT for natural language inference: A case study on the CommitmentBank","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"event-causality-recognition-exploiting","title":"Event Causality Recognition Exploiting Multiple Annotators' Judgments and Background Knowledge","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extract-and-aggregate-a-novel-domain","title":"Extract and Aggregate: A Novel Domain-Independent Approach to Factual Data Verification","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extractive-narrativeqa-with-heuristic-pre","title":"Extractive NarrativeQA with Heuristic Pre-Training","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/faspell-a-fast-adaptable-simple-powerful","slug":"faspell-a-fast-adaptable-simple-powerful","title":"FASPell: A Fast, Adaptable, Simple, Powerful Chinese Spell Checker Based On DAE-Decoder Paradigm","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-grained-propaganda-detection-with-fine","title":"Fine-Grained Propaganda Detection with Fine-Tuned BERT","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tune-bert-with-sparse-self-attention","title":"Fine-tune BERT with Sparse Self-Attention Mechanism","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"from-monolingual-to-multilingual-faq","title":"From Monolingual to Multilingual FAQ Assistant using Multilingual Co-training","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fully-unsupervised-crosslingual-semantic","title":"Fully Unsupervised Crosslingual Semantic Textual Similarity Metric Based on BERT for Identifying Parallel Data","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"3e3ab462e91c42da279029811bfe72c444e5a72832e8a75f63f34e8a83769bf2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}