{"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":"/task/language-modeling/papers/53","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":53,"pages_in_order":142,"rows_per_page":100,"rows":[5201,5300],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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":"/task/language-modeling","prev":"/task/language-modeling/papers/52","next":"/task/language-modeling/papers/54","papers":[{"url":"/paper/sibert-enhanced-chinese-pre-trained-language","slug":"sibert-enhanced-chinese-pre-trained-language","title":"SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/thailmcut-unsupervised-pretraining-for-thai","slug":"thailmcut-unsupervised-pretraining-for-thai","title":"ThaiLMCut: Unsupervised Pretraining for Thai Word Segmentation","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ampersand-argument-mining-for-persuasive-1","slug":"ampersand-argument-mining-for-persuasive-1","title":"AMPERSAND: Argument Mining for PERSuAsive oNline Discussions","date":"2020-04-30","arxiv_id":"2004.14677","repositories_listed":1,"syntology":null},{"url":"/paper/aspect-controlled-neural-argument-generation","slug":"aspect-controlled-neural-argument-generation","title":"Aspect-Controlled Neural Argument Generation","date":"2020-04-30","arxiv_id":"2005.00084","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-transferability-in-pretrained","slug":"investigating-transferability-in-pretrained","title":"Investigating Transferability in Pretrained Language Models","date":"2020-04-30","arxiv_id":"2004.14975","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/investigating-transferability-in-pretrained#ran","syntology_url":"https://syntology.ai/paper/2004.14975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14975"}},"official":{"repos":["dgiova/bert-lm-transferability"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/language-model-prior-for-low-resource-neural","slug":"language-model-prior-for-low-resource-neural","title":"Language Model Prior for Low-Resource Neural Machine Translation","date":"2020-04-30","arxiv_id":"2004.14928","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_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","sample_list":"/paper/language-model-prior-for-low-resource-neural#ran","syntology_url":"https://syntology.ai/paper/2004.14928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14928"}},"official":{"repos":["cbaziotis/lm-prior-for-nmt"],"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"]}}},{"url":"/paper/modelling-suspense-in-short-stories-as","slug":"modelling-suspense-in-short-stories-as","title":"Modelling Suspense in Short Stories as Uncertainty Reduction over Neural Representation","date":"2020-04-30","arxiv_id":"2004.14905","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modelling-suspense-in-short-stories-as#ran","syntology_url":"https://syntology.ai/paper/2004.14905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14905"}},"official":{"repos":["dwlmt/Story-Untangling"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/perturbed-masking-parameter-free-probing-for","slug":"perturbed-masking-parameter-free-probing-for","title":"Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT","date":"2020-04-30","arxiv_id":"2004.14786","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/perturbed-masking-parameter-free-probing-for#ran","syntology_url":"https://syntology.ai/paper/2004.14786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14786"}},"official":{"repos":["LividWo/Perturbed-Masking"],"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"]}}},{"url":"/paper/segabert-pre-training-of-segment-aware-bert","slug":"segabert-pre-training-of-segment-aware-bert","title":"Segatron: Segment-Aware Transformer for Language Modeling and Understanding","date":"2020-04-30","arxiv_id":"2004.14996","repositories_listed":1,"syntology":null},{"url":"/paper/analysing-lexical-semantic-change-with","slug":"analysing-lexical-semantic-change-with","title":"Analysing Lexical Semantic Change with Contextualised Word Representations","date":"2020-04-29","arxiv_id":"2004.14118","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/analysing-lexical-semantic-change-with#ran","syntology_url":"https://syntology.ai/paper/2004.14118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14118"}},"official":{"repos":["glnmario/cwr4lsc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/empower-entity-set-expansion-via-language","slug":"empower-entity-set-expansion-via-language","title":"Empower Entity Set Expansion via Language Model Probing","date":"2020-04-29","arxiv_id":"2004.13897","repositories_listed":1,"syntology":null},{"url":"/paper/expansion-via-prediction-of-importance-with","slug":"expansion-via-prediction-of-importance-with","title":"Expansion via Prediction of Importance with Contextualization","date":"2020-04-29","arxiv_id":"2004.14245","repositories_listed":1,"syntology":null},{"url":"/paper/geppetto-carves-italian-into-a-language-model","slug":"geppetto-carves-italian-into-a-language-model","title":"GePpeTto Carves Italian into a Language Model","date":"2020-04-29","arxiv_id":"2004.14253","repositories_listed":1,"syntology":null},{"url":"/paper/meta-transfer-learning-for-code-switched","slug":"meta-transfer-learning-for-code-switched","title":"Meta-Transfer Learning for Code-Switched Speech Recognition","date":"2020-04-29","arxiv_id":"2004.14228","repositories_listed":1,"syntology":null},{"url":"/paper/dombert-domain-oriented-language-model-for","slug":"dombert-domain-oriented-language-model-for","title":"DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis","date":"2020-04-28","arxiv_id":"2004.13816","repositories_listed":1,"syntology":null},{"url":"/paper/kungfupanda-at-semeval-2020-task-12-bert","slug":"kungfupanda-at-semeval-2020-task-12-bert","title":"Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection","date":"2020-04-28","arxiv_id":"2004.13432","repositories_listed":1,"syntology":null},{"url":"/paper/a-batch-normalized-inference-network-keeps","slug":"a-batch-normalized-inference-network-keeps","title":"A Batch Normalized Inference Network Keeps the KL Vanishing Away","date":"2020-04-27","arxiv_id":"2004.12585","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/a-batch-normalized-inference-network-keeps#ran","syntology_url":"https://syntology.ai/paper/2004.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12585"}},"official":{"repos":["valdersoul/bn-vae"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-512-tokens-siamese-multi-depth","slug":"beyond-512-tokens-siamese-multi-depth","title":"Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching","date":"2020-04-26","arxiv_id":"2004.12297","repositories_listed":1,"syntology":null},{"url":"/paper/a-tailored-pre-training-model-for-task","slug":"a-tailored-pre-training-model-for-task","title":"A Tailored Pre-Training Model for Task-Oriented Dialog Generation","date":"2020-04-24","arxiv_id":"2004.13835","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-information-retrieval-with-bert","slug":"cross-lingual-information-retrieval-with-bert","title":"Cross-lingual Information Retrieval with BERT","date":"2020-04-24","arxiv_id":"2004.13005","repositories_listed":1,"syntology":null},{"url":"/paper/template-based-question-generation-from","slug":"template-based-question-generation-from","title":"Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering","date":"2020-04-24","arxiv_id":"2004.11892","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/template-based-question-generation-from#ran","syntology_url":"https://syntology.ai/paper/2004.11892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.11892"}},"official":{"repos":["awslabs/unsupervised-qa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-tool-for-facilitating-ocr-postediting-in","slug":"a-tool-for-facilitating-ocr-postediting-in","title":"A Tool for Facilitating OCR Postediting in Historical Documents","date":"2020-04-23","arxiv_id":"2004.11471","repositories_listed":1,"syntology":null},{"url":"/paper/residual-energy-based-models-for-text-1","slug":"residual-energy-based-models-for-text-1","title":"Residual Energy-Based Models for Text Generation","date":"2020-04-22","arxiv_id":"2004.11714","repositories_listed":1,"syntology":null},{"url":"/paper/considering-likelihood-in-nlp-classification","slug":"considering-likelihood-in-nlp-classification","title":"Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling","date":"2020-04-21","arxiv_id":"2004.09890","repositories_listed":1,"syntology":null},{"url":"/paper/train-no-evil-selective-masking-for-task","slug":"train-no-evil-selective-masking-for-task","title":"Train No Evil: Selective Masking for Task-Guided Pre-Training","date":"2020-04-21","arxiv_id":"2004.09733","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/train-no-evil-selective-masking-for-task#ran","syntology_url":"https://syntology.ai/paper/2004.09733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.09733"}},"official":{"repos":["thunlp/SelectiveMasking"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-encoder-decoder-incompatibility-in","slug":"on-the-encoder-decoder-incompatibility-in","title":"On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond","date":"2020-04-20","arxiv_id":"2004.09189","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-attention-span-in-computer-vision","slug":"adaptive-attention-span-in-computer-vision","title":"Adaptive Attention Span in Computer Vision","date":"2020-04-18","arxiv_id":"2004.08708","repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-accurate-deep-bidirectional-language","slug":"fast-and-accurate-deep-bidirectional-language","title":"Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning","date":"2020-04-17","arxiv_id":"2004.08097","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/fast-and-accurate-deep-bidirectional-language#ran","syntology_url":"https://syntology.ai/paper/2004.08097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08097"}},"official":{"repos":["joongbo/tta"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/transform-and-tell-entity-aware-news-image","slug":"transform-and-tell-entity-aware-news-image","title":"Transform and Tell: Entity-Aware News Image Captioning","date":"2020-04-17","arxiv_id":"2004.08070","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transform-and-tell-entity-aware-news-image#ran","syntology_url":"https://syntology.ai/paper/2004.08070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08070"}},"official":{"repos":["alasdairtran/transform-and-tell"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/entities-as-experts-sparse-memory-access-with","slug":"entities-as-experts-sparse-memory-access-with","title":"Entities as Experts: Sparse Memory Access with Entity Supervision","date":"2020-04-15","arxiv_id":"2004.07202","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/entities-as-experts-sparse-memory-access-with#ran","syntology_url":"https://syntology.ai/paper/2004.07202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07202"}},"official":null}},{"url":"/paper/tod-bert-pre-trained-natural-language","slug":"tod-bert-pre-trained-natural-language","title":"TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue","date":"2020-04-15","arxiv_id":"2004.06871","repositories_listed":1,"syntology":{"n":13,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":13,"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) · 9 unverified","sample_list":"/paper/tod-bert-pre-trained-natural-language#ran","syntology_url":"https://syntology.ai/paper/2004.06871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06871"}},"official":{"repos":["jasonwu0731/ToD-BERT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-commonsense-question-answering","slug":"unsupervised-commonsense-question-answering","title":"Unsupervised Commonsense Question Answering with Self-Talk","date":"2020-04-11","arxiv_id":"2004.05483","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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) · 4 unverified","sample_list":"/paper/unsupervised-commonsense-question-answering#ran","syntology_url":"https://syntology.ai/paper/2004.05483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.05483"}},"official":{"repos":["vered1986/self_talk"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/downstream-model-design-of-pre-trained","slug":"downstream-model-design-of-pre-trained","title":"Downstream Model Design of Pre-trained Language Model for Relation Extraction Task","date":"2020-04-08","arxiv_id":"2004.03786","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-versatile-generative-language-model","slug":"exploring-versatile-generative-language-model","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","date":"2020-04-08","arxiv_id":"2004.03829","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/exploring-versatile-generative-language-model#ran","syntology_url":"https://syntology.ai/paper/2004.03829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03829"}},"official":{"repos":["zlinao/VGLM"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/have-your-text-and-use-it-too-end-to-end","slug":"have-your-text-and-use-it-too-end-to-end","title":"Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity","date":"2020-04-08","arxiv_id":"2004.06577","repositories_listed":1,"syntology":null},{"url":"/paper/byte-pair-encoding-is-suboptimal-for-language","slug":"byte-pair-encoding-is-suboptimal-for-language","title":"Byte Pair Encoding is Suboptimal for Language Model Pretraining","date":"2020-04-07","arxiv_id":"2004.03720","repositories_listed":1,"syntology":null},{"url":"/paper/transformers-to-learn-hierarchical-contexts","slug":"transformers-to-learn-hierarchical-contexts","title":"Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering","date":"2020-04-07","arxiv_id":"2004.03561","repositories_listed":1,"syntology":null},{"url":"/paper/selfore-self-supervised-relational-feature","slug":"selfore-self-supervised-relational-feature","title":"SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction","date":"2020-04-06","arxiv_id":"2004.02438","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-text-generation","slug":"sparse-text-generation","title":"Sparse Text Generation","date":"2020-04-06","arxiv_id":"2004.02644","repositories_listed":1,"syntology":null},{"url":"/paper/optimus-organizing-sentences-via-pre-trained","slug":"optimus-organizing-sentences-via-pre-trained","title":"Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space","date":"2020-04-05","arxiv_id":"2004.04092","repositories_listed":1,"syntology":null},{"url":"/paper/semantics-of-the-unwritten","slug":"semantics-of-the-unwritten","title":"Semantics of the Unwritten: The Effect of End of Paragraph and Sequence Tokens on Text Generation with GPT2","date":"2020-04-05","arxiv_id":"2004.02251","repositories_listed":1,"syntology":null},{"url":"/paper/memcap-memorizing-style-knowledge-for-image","slug":"memcap-memorizing-style-knowledge-for-image","title":"MemCap: Memorizing Style Knowledge for Image Captioning","date":"2020-04-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nukebert-a-pre-trained-language-model-for-low","slug":"nukebert-a-pre-trained-language-model-for-low","title":"NukeBERT: A Pre-trained language model for Low Resource Nuclear Domain","date":"2020-03-30","arxiv_id":"2003.13821","repositories_listed":1,"syntology":null},{"url":"/paper/abstractive-text-summarization-based-on","slug":"abstractive-text-summarization-based-on","title":"Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling","date":"2020-03-29","arxiv_id":"2003.13027","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/abstractive-text-summarization-based-on#ran","syntology_url":"https://syntology.ai/paper/2003.13027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13027"}},"official":{"repos":["axenov/BERT-Summ-OpenNMT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/common-knowledge-concept-recognition-for-seva","slug":"common-knowledge-concept-recognition-for-seva","title":"Common-Knowledge Concept Recognition for SEVA","date":"2020-03-26","arxiv_id":"2003.11687","repositories_listed":1,"syntology":null},{"url":"/paper/tnt-kid-transformer-based-neural-tagger-for","slug":"tnt-kid-transformer-based-neural-tagger-for","title":"TNT-KID: Transformer-based Neural Tagger for Keyword Identification","date":"2020-03-20","arxiv_id":"2003.09166","repositories_listed":1,"syntology":null},{"url":"/paper/recipegpt-generative-pre-training-based","slug":"recipegpt-generative-pre-training-based","title":"RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System","date":"2020-03-05","arxiv_id":"2003.02498","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-contexts-inside-robot-and-human","slug":"understanding-contexts-inside-robot-and-human","title":"Understanding Contexts Inside Robot and Human Manipulation Tasks through a Vision-Language Model and Ontology System in a Video Stream","date":"2020-03-02","arxiv_id":"2003.01163","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-generative-model-for-fragment-based","slug":"a-deep-generative-model-for-fragment-based","title":"A Deep Generative Model for Fragment-Based Molecule Generation","date":"2020-02-28","arxiv_id":"2002.12826","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-sinkhorn-attention","slug":"sparse-sinkhorn-attention","title":"Sparse Sinkhorn Attention","date":"2020-02-26","arxiv_id":"2002.11296","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-speech-recognition-via-local","slug":"semi-supervised-speech-recognition-via-local","title":"Semi-Supervised Speech Recognition via Local Prior Matching","date":"2020-02-24","arxiv_id":"2002.10336","repositories_listed":1,"syntology":null},{"url":"/paper/fill-in-the-blanc-human-free-quality","slug":"fill-in-the-blanc-human-free-quality","title":"Fill in the BLANC: Human-free quality estimation of document summaries","date":"2020-02-23","arxiv_id":"2002.09836","repositories_listed":1,"syntology":null},{"url":"/paper/maxup-a-simple-way-to-improve-generalization","slug":"maxup-a-simple-way-to-improve-generalization","title":"MaxUp: A Simple Way to Improve Generalization of Neural Network Training","date":"2020-02-20","arxiv_id":"2002.09024","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/maxup-a-simple-way-to-improve-generalization#ran","syntology_url":"https://syntology.ai/paper/2002.09024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09024"}},"official":null}},{"url":"/paper/hierarchical-models-vs-transfer-learning-for","slug":"hierarchical-models-vs-transfer-learning-for","title":"A Systematic Comparison of Architectures for Document-Level Sentiment Classification","date":"2020-02-19","arxiv_id":"2002.08131","repositories_listed":1,"syntology":null},{"url":"/paper/lambert-layout-aware-language-modeling-using","slug":"lambert-layout-aware-language-modeling-using","title":"LAMBERT: Layout-Aware (Language) Modeling for information extraction","date":"2020-02-19","arxiv_id":"2002.08087","repositories_listed":1,"syntology":null},{"url":"/paper/200302645","slug":"200302645","title":"SentenceMIM: A Latent Variable Language Model","date":"2020-02-18","arxiv_id":"2003.02645","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/200302645#ran","syntology_url":"https://syntology.ai/paper/2003.02645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02645"}},"official":null}},{"url":"/paper/transformer-on-a-diet","slug":"transformer-on-a-diet","title":"Transformer on a Diet","date":"2020-02-14","arxiv_id":"2002.06170","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-for-source-code-modeling-and","slug":"deep-learning-for-source-code-modeling-and","title":"Deep Learning for Source Code Modeling and Generation: Models, Applications and Challenges","date":"2020-02-13","arxiv_id":"2002.05442","repositories_listed":1,"syntology":null},{"url":"/paper/blank-language-models","slug":"blank-language-models","title":"Blank Language Models","date":"2020-02-08","arxiv_id":"2002.03079","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/blank-language-models#ran","syntology_url":"https://syntology.ai/paper/2002.03079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.03079"}},"official":{"repos":["Varal7/blank_language_model"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/time-aware-large-kernel-convolutions","slug":"time-aware-large-kernel-convolutions","title":"Time-aware Large Kernel Convolutions","date":"2020-02-08","arxiv_id":"2002.03184","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":2,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/time-aware-large-kernel-convolutions#ran","syntology_url":"https://syntology.ai/paper/2002.03184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.03184"}},"official":{"repos":["lioutasb/TaLKConvolutions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/consistency-of-a-recurrent-language-model","slug":"consistency-of-a-recurrent-language-model","title":"Consistency of a Recurrent Language Model With Respect to Incomplete Decoding","date":"2020-02-06","arxiv_id":"2002.02492","repositories_listed":1,"syntology":null},{"url":"/paper/introducing-aspects-of-creativity-in","slug":"introducing-aspects-of-creativity-in","title":"Introducing Aspects of Creativity in Automatic Poetry Generation","date":"2020-02-06","arxiv_id":"2002.02511","repositories_listed":1,"syntology":null},{"url":"/paper/citation-text-generation","slug":"citation-text-generation","title":"Explaining Relationships Between Scientific Documents","date":"2020-02-02","arxiv_id":"2002.00317","repositories_listed":1,"syntology":null},{"url":"/paper/contextualized-embeddings-in-named-entity","slug":"contextualized-embeddings-in-named-entity","title":"Contextualized Embeddings in Named-Entity Recognition: An Empirical Study on Generalization","date":"2020-01-22","arxiv_id":"2001.08053","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-domain-adaptation-for-neural-2","slug":"unsupervised-domain-adaptation-for-neural-2","title":"A Simple Baseline to Semi-Supervised Domain Adaptation for Machine Translation","date":"2020-01-22","arxiv_id":"2001.08140","repositories_listed":1,"syntology":null},{"url":"/paper/domain-aware-dialogue-state-tracker-for-multi","slug":"domain-aware-dialogue-state-tracker-for-multi","title":"Domain-Aware Dialogue State Tracker for Multi-Domain Dialogue Systems","date":"2020-01-21","arxiv_id":"2001.07526","repositories_listed":1,"syntology":null},{"url":"/paper/robbert-a-dutch-roberta-based-language-model","slug":"robbert-a-dutch-roberta-based-language-model","title":"RobBERT: a Dutch RoBERTa-based Language Model","date":"2020-01-17","arxiv_id":"2001.06286","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/robbert-a-dutch-roberta-based-language-model#ran","syntology_url":"https://syntology.ai/paper/2001.06286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06286"}},"official":{"repos":["iPieter/RobBERT"],"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"]}}},{"url":"/paper/block-wise-dynamic-sparseness","slug":"block-wise-dynamic-sparseness","title":"Block-wise Dynamic Sparseness","date":"2020-01-14","arxiv_id":"2001.04686","repositories_listed":1,"syntology":null},{"url":"/paper/montage-a-neural-network-language-model","slug":"montage-a-neural-network-language-model","title":"Montage: A Neural Network Language Model-Guided JavaScript Engine Fuzzer","date":"2020-01-13","arxiv_id":"2001.04107","repositories_listed":1,"syntology":null},{"url":"/paper/improving-transformer-optimization-through","slug":"improving-transformer-optimization-through","title":"Improving Transformer Optimization Through Better Initialization","date":"2020-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-transformer-optimization-through-1","slug":"improving-transformer-optimization-through-1","title":"Improving Transformer Optimization Through Better Initialization","date":"2020-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pseudo-masked-language-models-for-unified","slug":"pseudo-masked-language-models-for-unified","title":"Pseudo-Masked Language Models for Unified Language Model Pre-Training","date":"2020-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/encoding-word-order-in-complex-embeddings-1","slug":"encoding-word-order-in-complex-embeddings-1","title":"Encoding word order in complex embeddings","date":"2019-12-27","arxiv_id":"1912.12333","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-hierarchical-topic-guided-neural-1","slug":"recurrent-hierarchical-topic-guided-neural-1","title":"Recurrent Hierarchical Topic-Guided RNN for Language Generation","date":"2019-12-21","arxiv_id":"1912.10337","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-named-entity-recognition-and-1","slug":"end-to-end-named-entity-recognition-and-1","title":"End-to-end Named Entity Recognition and Relation Extraction using Pre-trained Language Models","date":"2019-12-20","arxiv_id":"1912.13415","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-character-embeddings-learning","slug":"hierarchical-character-embeddings-learning","title":"Hierarchical Character Embeddings: Learning Phonological and Semantic Representations in Languages of Logographic Origin using Recursive Neural Networks","date":"2019-12-20","arxiv_id":"1912.09913","repositories_listed":1,"syntology":null},{"url":"/paper/generating-synthetic-audio-data-for-attention","slug":"generating-synthetic-audio-data-for-attention","title":"Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems","date":"2019-12-19","arxiv_id":"1912.09257","repositories_listed":1,"syntology":null},{"url":"/paper/neural-academic-paper-generation","slug":"neural-academic-paper-generation","title":"Neural Academic Paper Generation","date":"2019-12-02","arxiv_id":"1912.01982","repositories_listed":1,"syntology":null},{"url":"/paper/data-differentiable-architecture","slug":"data-differentiable-architecture","title":"DATA: Differentiable ArchiTecture Approximation","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/memory-efficient-adaptive-optimization","slug":"memory-efficient-adaptive-optimization","title":"Memory Efficient Adaptive Optimization","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-shuffle-exchange-networks-sequence-1","slug":"neural-shuffle-exchange-networks-sequence-1","title":"Neural Shuffle-Exchange Networks - Sequence Processing in O(n log n) Time","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pythia-ai-assisted-code-completion-system","slug":"pythia-ai-assisted-code-completion-system","title":"Pythia: AI-assisted Code Completion System","date":"2019-11-29","arxiv_id":"1912.00742","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pythia-ai-assisted-code-completion-system#ran","syntology_url":"https://syntology.ai/paper/1912.00742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00742"}},"official":{"repos":["Microsoft/PTVS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-commonsense-in-pre-trained","slug":"evaluating-commonsense-in-pre-trained","title":"Evaluating Commonsense in Pre-trained Language Models","date":"2019-11-27","arxiv_id":"1911.11931","repositories_listed":1,"syntology":null},{"url":"/paper/autoencoding-undirected-molecular-graphs-with","slug":"autoencoding-undirected-molecular-graphs-with","title":"Autoencoding Undirected Molecular Graphs With Neural Networks","date":"2019-11-26","arxiv_id":"2001.03517","repositories_listed":1,"syntology":null},{"url":"/paper/emotional-neural-language-generation-grounded","slug":"emotional-neural-language-generation-grounded","title":"Emotional Neural Language Generation Grounded in Situational Contexts","date":"2019-11-25","arxiv_id":"1911.11161","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-of-deep-bidirectional-protein","slug":"pre-training-of-deep-bidirectional-protein","title":"Pre-Training of Deep Bidirectional Protein Sequence Representations with Structural Information","date":"2019-11-25","arxiv_id":"1912.05625","repositories_listed":1,"syntology":null},{"url":"/paper/controlling-the-amount-of-verbatim-copying-in","slug":"controlling-the-amount-of-verbatim-copying-in","title":"Controlling the Amount of Verbatim Copying in Abstractive Summarization","date":"2019-11-23","arxiv_id":"1911.10390","repositories_listed":1,"syntology":null},{"url":"/paper/continual-adaptation-for-efficient-machine","slug":"continual-adaptation-for-efficient-machine","title":"Continual adaptation for efficient machine communication","date":"2019-11-22","arxiv_id":"1911.09896","repositories_listed":1,"syntology":null},{"url":"/paper/red-dragon-ai-at-textgraphs-2019-shared-task-1","slug":"red-dragon-ai-at-textgraphs-2019-shared-task-1","title":"Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation","date":"2019-11-20","arxiv_id":"1911.08976","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-asr-from-supervised-to-semi","slug":"end-to-end-asr-from-supervised-to-semi","title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","date":"2019-11-19","arxiv_id":"1911.08460","repositories_listed":1,"syntology":null},{"url":"/paper/kepler-a-unified-model-for-knowledge","slug":"kepler-a-unified-model-for-knowledge","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","date":"2019-11-13","arxiv_id":"1911.06136","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/kepler-a-unified-model-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/1911.06136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06136"}},"official":{"repos":["THU-KEG/KEPLER"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/smiles-transformer-pre-trained-molecular","slug":"smiles-transformer-pre-trained-molecular","title":"SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery","date":"2019-11-12","arxiv_id":"1911.04738","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/smiles-transformer-pre-trained-molecular#ran","syntology_url":"https://syntology.ai/paper/1911.04738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04738"}},"official":{"repos":["DSPsleeporg/smiles-transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/conditionally-learn-to-pay-attention-for","slug":"conditionally-learn-to-pay-attention-for","title":"Conditionally Learn to Pay Attention for Sequential Visual Task","date":"2019-11-11","arxiv_id":"1911.04365","repositories_listed":1,"syntology":null},{"url":"/paper/searching-for-legal-clauses-by-analogy-few","slug":"searching-for-legal-clauses-by-analogy-few","title":"Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines","date":"2019-11-10","arxiv_id":"1911.03911","repositories_listed":1,"syntology":null},{"url":"/paper/on-architectures-for-including-visual","slug":"on-architectures-for-including-visual","title":"On Architectures for Including Visual Information in Neural Language Models for Image Description","date":"2019-11-09","arxiv_id":"1911.03738","repositories_listed":1,"syntology":null},{"url":"/paper/not-enough-data-deep-learning-to-the-rescue","slug":"not-enough-data-deep-learning-to-the-rescue","title":"Not Enough Data? Deep Learning to the Rescue!","date":"2019-11-08","arxiv_id":"1911.03118","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/improving-grammatical-error-correction-with","slug":"improving-grammatical-error-correction-with","title":"Improving Grammatical Error Correction with Machine Translation Pairs","date":"2019-11-07","arxiv_id":"1911.02825","repositories_listed":1,"syntology":null},{"url":"/paper/sentilr-linguistic-knowledge-enhanced","slug":"sentilr-linguistic-knowledge-enhanced","title":"SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge","date":"2019-11-06","arxiv_id":"1911.02493","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-grounding-of-natural-language","slug":"contextual-grounding-of-natural-language","title":"Contextual Grounding of Natural Language Entities in Images","date":"2019-11-05","arxiv_id":"1911.02133","repositories_listed":1,"syntology":null}],"record_sha256":"511b5726bddda3d6fbe2f4bd7755ff4e7faff41cf0edcd137ec71420b6332c67","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}