{"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-modelling/papers/12","list_of":"/task/language-modelling","task":"Language Modelling","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":12,"pages_in_order":177,"rows_per_page":100,"rows":[1101,1200],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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-modelling","prev":"/task/language-modelling/papers/11","next":"/task/language-modelling/papers/13","papers":[{"url":"/paper/discrete-optimization-for-unsupervised","slug":"discrete-optimization-for-unsupervised","title":"Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction","date":"2020-05-04","arxiv_id":"2005.01791","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/discrete-optimization-for-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2005.01791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.01791"}},"official":{"repos":["raphael-sch/HC_Sentence_Summarization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/on-faithfulness-and-factuality-in-abstractive","slug":"on-faithfulness-and-factuality-in-abstractive","title":"On Faithfulness and Factuality in Abstractive Summarization","date":"2020-05-02","arxiv_id":"2005.00661","repositories_listed":2,"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/on-faithfulness-and-factuality-in-abstractive#ran","syntology_url":"https://syntology.ai/paper/2005.00661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00661"}},"official":{"repos":["google-research-datasets/xsum_hallucination_annotations"],"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/unifiedqa-crossing-format-boundaries-with-a","slug":"unifiedqa-crossing-format-boundaries-with-a","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","date":"2020-05-02","arxiv_id":"2005.00700","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unifiedqa-crossing-format-boundaries-with-a#ran","syntology_url":"https://syntology.ai/paper/2005.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00700"}},"official":{"repos":["allenai/unifiedqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/visually-grounded-continual-learning-of","slug":"visually-grounded-continual-learning-of","title":"Visually Grounded Continual Learning of Compositional Phrases","date":"2020-05-02","arxiv_id":"2005.00785","repositories_listed":2,"syntology":null},{"url":"/paper/pretraining-on-non-linguistic-structure-as-a","slug":"pretraining-on-non-linguistic-structure-as-a","title":"Learning Music Helps You Read: Using Transfer to Study Linguistic Structure in Language Models","date":"2020-04-30","arxiv_id":"2004.14601","repositories_listed":2,"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":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pretraining-on-non-linguistic-structure-as-a#ran","syntology_url":"https://syntology.ai/paper/2004.14601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14601"}},"official":{"repos":["toizzy/tilt-transfer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lite-transformer-with-long-short-range","slug":"lite-transformer-with-long-short-range","title":"Lite Transformer with Long-Short Range Attention","date":"2020-04-24","arxiv_id":"2004.11886","repositories_listed":2,"syntology":null},{"url":"/paper/rigid-formats-controlled-text-generation","slug":"rigid-formats-controlled-text-generation","title":"SongNet: Rigid Formats Controlled Text Generation","date":"2020-04-17","arxiv_id":"2004.08022","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":1,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rigid-formats-controlled-text-generation#ran","syntology_url":"https://syntology.ai/paper/2004.08022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08022"}},"official":{"repos":["lipiji/SongNet"],"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":["listed","official"]}}},{"url":"/paper/palm-pre-training-an-autoencoding","slug":"palm-pre-training-an-autoencoding","title":"PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation","date":"2020-04-14","arxiv_id":"2004.07159","repositories_listed":2,"syntology":null},{"url":"/paper/injecting-numerical-reasoning-skills-into","slug":"injecting-numerical-reasoning-skills-into","title":"Injecting Numerical Reasoning Skills into Language Models","date":"2020-04-09","arxiv_id":"2004.04487","repositories_listed":2,"syntology":null},{"url":"/paper/residual-shuffle-exchange-networks-for-fast","slug":"residual-shuffle-exchange-networks-for-fast","title":"Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences","date":"2020-04-06","arxiv_id":"2004.04662","repositories_listed":2,"syntology":null},{"url":"/paper/meta-fine-tuning-neural-language-models-for","slug":"meta-fine-tuning-neural-language-models-for","title":"Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining","date":"2020-03-29","arxiv_id":"2003.13003","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-content-based-sparse-attention-with-1","slug":"efficient-content-based-sparse-attention-with-1","title":"Efficient Content-Based Sparse Attention with Routing Transformers","date":"2020-03-12","arxiv_id":"2003.05997","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-content-based-sparse-attention-with-1#ran","syntology_url":"https://syntology.ai/paper/2003.05997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05997"}},"official":null}},{"url":"/paper/progen-language-modeling-for-protein","slug":"progen-language-modeling-for-protein","title":"ProGen: Language Modeling for Protein Generation","date":"2020-03-08","arxiv_id":"2004.03497","repositories_listed":2,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":7,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/progen-language-modeling-for-protein#ran","syntology_url":"https://syntology.ai/paper/2004.03497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03497"}},"official":null}},{"url":"/paper/cluecorpus2020-a-large-scale-chinese-corpus","slug":"cluecorpus2020-a-large-scale-chinese-corpus","title":"CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model","date":"2020-03-03","arxiv_id":"2003.01355","repositories_listed":2,"syntology":null},{"url":"/paper/language-as-a-cognitive-tool-to-imagine-goals","slug":"language-as-a-cognitive-tool-to-imagine-goals","title":"Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration","date":"2020-02-21","arxiv_id":"2002.09253","repositories_listed":2,"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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/language-as-a-cognitive-tool-to-imagine-goals#ran","syntology_url":"https://syntology.ai/paper/2002.09253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09253"}},"official":{"repos":["flowersteam/Imagine","flowersteam/playground_env"],"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/second-order-optimization-made-practical","slug":"second-order-optimization-made-practical","title":"Scalable Second Order Optimization for Deep Learning","date":"2020-02-20","arxiv_id":"2002.09018","repositories_listed":2,"syntology":null},{"url":"/paper/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/univilm-a-unified-video-and-language-pre#ran","syntology_url":"https://syntology.ai/paper/2002.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06353"}},"official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/learninghome-crowdsourced-training-of-large","slug":"learninghome-crowdsourced-training-of-large","title":"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts","date":"2020-02-10","arxiv_id":"2002.04013","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/learninghome-crowdsourced-training-of-large#ran","syntology_url":"https://syntology.ai/paper/2002.04013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.04013"}},"official":{"repos":["mryab/learning-at-home"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/parsing-as-pretraining","slug":"parsing-as-pretraining","title":"Parsing as Pretraining","date":"2020-02-05","arxiv_id":"2002.01685","repositories_listed":2,"syntology":{"n":30,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":17,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/parsing-as-pretraining#ran","syntology_url":"https://syntology.ai/paper/2002.01685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.01685"}},"official":{"repos":["aghie/parsing-as-pretraining"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/scaling-laws-for-neural-language-models","slug":"scaling-laws-for-neural-language-models","title":"Scaling Laws for Neural Language Models","date":"2020-01-23","arxiv_id":"2001.08361","repositories_listed":2,"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/scaling-laws-for-neural-language-models#ran","syntology_url":"https://syntology.ai/paper/2001.08361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.08361"}},"official":null}},{"url":"/paper/olmpics-on-what-language-model-pre-training","slug":"olmpics-on-what-language-model-pre-training","title":"oLMpics -- On what Language Model Pre-training Captures","date":"2019-12-31","arxiv_id":"1912.13283","repositories_listed":2,"syntology":null},{"url":"/paper/explicit-sparse-transformer-concentrated","slug":"explicit-sparse-transformer-concentrated","title":"Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection","date":"2019-12-25","arxiv_id":"1912.11637","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 1 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","sample_list":"/paper/explicit-sparse-transformer-concentrated#ran","syntology_url":"https://syntology.ai/paper/1912.11637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.11637"}},"official":{"repos":["lancopku/Explicit-Sparse-Transformer"],"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":["unlocated"]}}},{"url":"/paper/bertje-a-dutch-bert-model","slug":"bertje-a-dutch-bert-model","title":"BERTje: A Dutch BERT Model","date":"2019-12-19","arxiv_id":"1912.09582","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bertje-a-dutch-bert-model#ran","syntology_url":"https://syntology.ai/paper/1912.09582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.09582"}},"official":{"repos":["wietsedv/bertje"],"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"]}}},{"url":"/paper/a-feasible-framework-for-arbitrary-shaped","slug":"a-feasible-framework-for-arbitrary-shaped","title":"A Feasible Framework for Arbitrary-Shaped Scene Text Recognition","date":"2019-12-10","arxiv_id":"1912.04561","repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-pretraining-for-visual-dialog-a","slug":"large-scale-pretraining-for-visual-dialog-a","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","date":"2019-12-05","arxiv_id":"1912.02379","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/large-scale-pretraining-for-visual-dialog-a#ran","syntology_url":"https://syntology.ai/paper/1912.02379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02379"}},"official":{"repos":["vmurahari3/visdial-bert"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-pre-training-based-personalized-dialogue","slug":"a-pre-training-based-personalized-dialogue","title":"A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data","date":"2019-11-12","arxiv_id":"1911.04700","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-pre-training-based-personalized-dialogue#ran","syntology_url":"https://syntology.ai/paper/1911.04700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04700"}},"official":null}},{"url":"/paper/bp-transformer-modelling-long-range-context","slug":"bp-transformer-modelling-long-range-context","title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","date":"2019-11-11","arxiv_id":"1911.04070","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/bp-transformer-modelling-long-range-context#ran","syntology_url":"https://syntology.ai/paper/1911.04070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04070"}},"official":{"repos":["yzh119/BPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/distilling-the-knowledge-of-bert-for-text-1","slug":"distilling-the-knowledge-of-bert-for-text-1","title":"Distilling Knowledge Learned in BERT for Text Generation","date":"2019-11-10","arxiv_id":"1911.03829","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distilling-the-knowledge-of-bert-for-text-1#ran","syntology_url":"https://syntology.ai/paper/1911.03829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03829"}},"official":{"repos":["ChenRocks/Distill-BERT-Textgen"],"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/effectiveness-of-self-supervised-pre-training","slug":"effectiveness-of-self-supervised-pre-training","title":"Effectiveness of self-supervised pre-training for speech recognition","date":"2019-11-10","arxiv_id":"1911.03912","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/memory-augmented-recurrent-neural-networks","slug":"memory-augmented-recurrent-neural-networks","title":"Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages","date":"2019-11-08","arxiv_id":"1911.03329","repositories_listed":2,"syntology":null},{"url":"/paper/negated-lama-birds-cannot-fly","slug":"negated-lama-birds-cannot-fly","title":"Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly","date":"2019-11-08","arxiv_id":"1911.03343","repositories_listed":2,"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":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/negated-lama-birds-cannot-fly#ran","syntology_url":"https://syntology.ai/paper/1911.03343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03343"}},"official":{"repos":["facebookresearch/LAMA","norakassner/LAMA_primed_negated"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gorc-a-large-contextual-citation-graph-of","slug":"gorc-a-large-contextual-citation-graph-of","title":"S2ORC: The Semantic Scholar Open Research Corpus","date":"2019-11-07","arxiv_id":"1911.02782","repositories_listed":2,"syntology":null},{"url":"/paper/open-domain-web-keyphrase-extraction-beyond-1","slug":"open-domain-web-keyphrase-extraction-beyond-1","title":"Open Domain Web Keyphrase Extraction Beyond Language Modeling","date":"2019-11-06","arxiv_id":"1911.02671","repositories_listed":2,"syntology":null},{"url":"/paper/human-and-automatic-detection-of-generated","slug":"human-and-automatic-detection-of-generated","title":"Automatic Detection of Generated Text is Easiest when Humans are Fooled","date":"2019-11-02","arxiv_id":"1911.00650","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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) · 2 unverified","sample_list":"/paper/human-and-automatic-detection-of-generated#ran","syntology_url":"https://syntology.ai/paper/1911.00650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00650"}},"official":null}},{"url":"/paper/a-bert-based-transfer-learning-approach-for","slug":"a-bert-based-transfer-learning-approach-for","title":"A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media","date":"2019-10-28","arxiv_id":"1910.12574","repositories_listed":2,"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/a-bert-based-transfer-learning-approach-for#ran","syntology_url":"https://syntology.ai/paper/1910.12574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12574"}},"official":null}},{"url":"/paper/neural-generation-for-czech-data-and","slug":"neural-generation-for-czech-data-and","title":"Neural Generation for Czech: Data and Baselines","date":"2019-10-11","arxiv_id":"1910.05298","repositories_listed":2,"syntology":null},{"url":"/paper/structured-pruning-of-large-language-models","slug":"structured-pruning-of-large-language-models","title":"Structured Pruning of Large Language Models","date":"2019-10-10","arxiv_id":"1910.04732","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"8 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/structured-pruning-of-large-language-models#ran","syntology_url":"https://syntology.ai/paper/1910.04732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04732"}},"official":{"repos":["asappresearch/flop"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/the-merits-of-universal-language-model-fine","slug":"the-merits-of-universal-language-model-fine","title":"The merits of Universal Language Model Fine-tuning for Small Datasets -- a case with Dutch book reviews","date":"2019-10-02","arxiv_id":"1910.00896","repositories_listed":2,"syntology":null},{"url":"/paper/structural-language-models-for-any-code","slug":"structural-language-models-for-any-code","title":"Structural Language Models of Code","date":"2019-09-30","arxiv_id":"1910.00577","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/structural-language-models-for-any-code#ran","syntology_url":"https://syntology.ai/paper/1910.00577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00577"}},"official":{"repos":["tech-srl/slm-code-generation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fake-news-detection-using-deep-learning","slug":"fake-news-detection-using-deep-learning","title":"Fake news detection using Deep Learning","date":"2019-09-29","arxiv_id":"1910.03496","repositories_listed":2,"syntology":null},{"url":"/paper/mixout-effective-regularization-to-finetune","slug":"mixout-effective-regularization-to-finetune","title":"Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models","date":"2019-09-25","arxiv_id":"1909.11299","repositories_listed":2,"syntology":null},{"url":"/paper/bertgrid-contextualized-embedding-for-2d","slug":"bertgrid-contextualized-embedding-for-2d","title":"BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding","date":"2019-09-11","arxiv_id":"1909.04948","repositories_listed":2,"syntology":null},{"url":"/paper/taper-time-aware-patient-ehr-representation","slug":"taper-time-aware-patient-ehr-representation","title":"TAPER: Time-Aware Patient EHR Representation","date":"2019-08-11","arxiv_id":"1908.03971","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/taper-time-aware-patient-ehr-representation#ran","syntology_url":"https://syntology.ai/paper/1908.03971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03971"}},"official":{"repos":["sajaddarabi/TAPER","sajaddarabi/TAPER-EHR"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/what-bert-is-not-lessons-from-a-new-suite-of","slug":"what-bert-is-not-lessons-from-a-new-suite-of","title":"What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models","date":"2019-07-31","arxiv_id":"1907.13528","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 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; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/what-bert-is-not-lessons-from-a-new-suite-of#ran","syntology_url":"https://syntology.ai/paper/1907.13528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.13528"}},"official":{"repos":["aetting/lm-diagnostics"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/caire-an-end-to-end-empathetic-chatbot","slug":"caire-an-end-to-end-empathetic-chatbot","title":"CAiRE: An Empathetic Neural Chatbot","date":"2019-07-28","arxiv_id":"1907.12108","repositories_listed":2,"syntology":null},{"url":"/paper/r-transformer-recurrent-neural-network","slug":"r-transformer-recurrent-neural-network","title":"R-Transformer: Recurrent Neural Network Enhanced Transformer","date":"2019-07-12","arxiv_id":"1907.05572","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/r-transformer-recurrent-neural-network#ran","syntology_url":"https://syntology.ai/paper/1907.05572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.05572"}},"official":{"repos":["DSE-MSU/R-transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/to-tune-or-not-to-tune-how-about-the-best-of","slug":"to-tune-or-not-to-tune-how-about-the-best-of","title":"To Tune or Not To Tune? How About the Best of Both Worlds?","date":"2019-07-09","arxiv_id":"1907.05338","repositories_listed":2,"syntology":null},{"url":"/paper/augmenting-self-attention-with-persistent","slug":"augmenting-self-attention-with-persistent","title":"Augmenting Self-attention with Persistent Memory","date":"2019-07-02","arxiv_id":"1907.01470","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":3,"n_no_contract":0,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/augmenting-self-attention-with-persistent#ran","syntology_url":"https://syntology.ai/paper/1907.01470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.01470"}},"official":null}},{"url":"/paper/evaluating-language-model-finetuning","slug":"evaluating-language-model-finetuning","title":"Evaluating Language Model Finetuning Techniques for Low-resource Languages","date":"2019-06-30","arxiv_id":"1907.00409","repositories_listed":2,"syntology":null},{"url":"/paper/emotionx-ku-bert-max-based-contextual-emotion","slug":"emotionx-ku-bert-max-based-contextual-emotion","title":"EmotionX-KU: BERT-Max based Contextual Emotion Classifier","date":"2019-06-27","arxiv_id":"1906.11565","repositories_listed":2,"syntology":null},{"url":"/paper/multilingual-named-entity-recognition-using-1","slug":"multilingual-named-entity-recognition-using-1","title":"Multilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF","date":"2019-06-21","arxiv_id":"1906.09978","repositories_listed":2,"syntology":null},{"url":"/paper/pre-training-with-whole-word-masking-for","slug":"pre-training-with-whole-word-masking-for","title":"Pre-Training with Whole Word Masking for Chinese BERT","date":"2019-06-19","arxiv_id":"1906.08101","repositories_listed":2,"syntology":null},{"url":"/paper/towards-robust-named-entity-recognition-for","slug":"towards-robust-named-entity-recognition-for","title":"Towards Robust Named Entity Recognition for Historic German","date":"2019-06-18","arxiv_id":"1906.07592","repositories_listed":2,"syntology":null},{"url":"/paper/generating-question-answer-hierarchies","slug":"generating-question-answer-hierarchies","title":"Generating Question-Answer Hierarchies","date":"2019-06-06","arxiv_id":"1906.02622","repositories_listed":2,"syntology":null},{"url":"/paper/the-unreasonable-effectiveness-of-transformer","slug":"the-unreasonable-effectiveness-of-transformer","title":"The Unreasonable Effectiveness of Transformer Language Models in Grammatical Error Correction","date":"2019-06-04","arxiv_id":"1906.01733","repositories_listed":2,"syntology":null},{"url":"/paper/190600363","slug":"190600363","title":"Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation","date":"2019-06-02","arxiv_id":"1906.00363","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/190600363#ran","syntology_url":"https://syntology.ai/paper/1906.00363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00363"}},"official":{"repos":["wangcunxiang/Sen-Making-and-Explanation"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/190600283","slug":"190600283","title":"Learning to Generate Grounded Visual Captions without Localization Supervision","date":"2019-06-01","arxiv_id":"1906.00283","repositories_listed":2,"syntology":null},{"url":"/paper/cif-continuous-integrate-and-fire-for-end-to","slug":"cif-continuous-integrate-and-fire-for-end-to","title":"CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition","date":"2019-05-27","arxiv_id":"1905.11235","repositories_listed":2,"syntology":null},{"url":"/paper/discrete-flows-invertible-generative-models","slug":"discrete-flows-invertible-generative-models","title":"Discrete Flows: Invertible Generative Models of Discrete Data","date":"2019-05-24","arxiv_id":"1905.10347","repositories_listed":2,"syntology":null},{"url":"/paper/mu-forcing-training-variational-recurrent","slug":"mu-forcing-training-variational-recurrent","title":"mu-Forcing: Training Variational Recurrent Autoencoders for Text Generation","date":"2019-05-24","arxiv_id":"1905.10072","repositories_listed":2,"syntology":null},{"url":"/paper/sample-efficient-text-summarization-using-a","slug":"sample-efficient-text-summarization-using-a","title":"Sample Efficient Text Summarization Using a Single Pre-Trained Transformer","date":"2019-05-21","arxiv_id":"1905.08836","repositories_listed":2,"syntology":null},{"url":"/paper/190506596","slug":"190506596","title":"Joint Source-Target Self Attention with Locality Constraints","date":"2019-05-16","arxiv_id":"1905.06596","repositories_listed":2,"syntology":null},{"url":"/paper/a-surprisingly-robust-trick-for-winograd","slug":"a-surprisingly-robust-trick-for-winograd","title":"A Surprisingly Robust Trick for Winograd Schema Challenge","date":"2019-05-15","arxiv_id":"1905.06290","repositories_listed":2,"syntology":null},{"url":"/paper/what-do-you-learn-from-context-probing-for-1","slug":"what-do-you-learn-from-context-probing-for-1","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","date":"2019-05-15","arxiv_id":"1905.06316","repositories_listed":2,"syntology":null},{"url":"/paper/rwth-asr-systems-for-librispeech-hybrid-vs","slug":"rwth-asr-systems-for-librispeech-hybrid-vs","title":"RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation","date":"2019-05-08","arxiv_id":"1905.03072","repositories_listed":2,"syntology":null},{"url":"/paper/adversarial-dropout-for-recurrent-neural","slug":"adversarial-dropout-for-recurrent-neural","title":"Adversarial Dropout for Recurrent Neural Networks","date":"2019-04-22","arxiv_id":"1904.09816","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-nlg-with-pre-trained-language-model","slug":"few-shot-nlg-with-pre-trained-language-model","title":"Few-Shot NLG with Pre-Trained Language Model","date":"2019-04-21","arxiv_id":"1904.09521","repositories_listed":2,"syntology":null},{"url":"/paper/190409324","slug":"190409324","title":"Mask-Predict: Parallel Decoding of Conditional Masked Language Models","date":"2019-04-19","arxiv_id":"1904.09324","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/190409324#ran","syntology_url":"https://syntology.ai/paper/1904.09324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09324"}},"official":{"repos":["facebookresearch/Mask-Predict"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/pun-generation-with-surprise","slug":"pun-generation-with-surprise","title":"Pun Generation with Surprise","date":"2019-04-15","arxiv_id":"1904.06828","repositories_listed":2,"syntology":null},{"url":"/paper/rare-words-a-major-problem-for-contextualized","slug":"rare-words-a-major-problem-for-contextualized","title":"Rare Words: A Major Problem for Contextualized Embeddings And How to Fix it by Attentive Mimicking","date":"2019-04-14","arxiv_id":"1904.06707","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rare-words-a-major-problem-for-contextualized#ran","syntology_url":"https://syntology.ai/paper/1904.06707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.06707"}},"official":{"repos":["timoschick/am-for-bert","timoschick/one-token-approximation"],"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/cyclical-annealing-schedule-a-simple-approach","slug":"cyclical-annealing-schedule-a-simple-approach","title":"Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing","date":"2019-03-25","arxiv_id":"1903.10145","repositories_listed":2,"syntology":null},{"url":"/paper/improving-lemmatization-of-non-standard","slug":"improving-lemmatization-of-non-standard","title":"Improving Lemmatization of Non-Standard Languages with Joint Learning","date":"2019-03-16","arxiv_id":"1903.06939","repositories_listed":2,"syntology":null},{"url":"/paper/glyce-glyph-vectors-for-chinese-character","slug":"glyce-glyph-vectors-for-chinese-character","title":"Glyce: Glyph-vectors for Chinese Character Representations","date":"2019-01-29","arxiv_id":"1901.10125","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glyce-glyph-vectors-for-chinese-character#ran","syntology_url":"https://syntology.ai/paper/1901.10125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10125"}},"official":{"repos":["ShannonAI/glyce"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-user-modeling-with-long-and-short","slug":"adaptive-user-modeling-with-long-and-short","title":"Adaptive User Modeling with Long and Short-Term Preferences for Personalized Recommendation","date":"2019-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/knowledge-representation-learning-a","slug":"knowledge-representation-learning-a","title":"Knowledge Representation Learning: A Quantitative Review","date":"2018-12-28","arxiv_id":"1812.10901","repositories_listed":2,"syntology":null},{"url":"/paper/compositional-language-understanding-with","slug":"compositional-language-understanding-with","title":"Compositional Language Understanding with Text-based Relational Reasoning","date":"2018-11-07","arxiv_id":"1811.02959","repositories_listed":2,"syntology":null},{"url":"/paper/universal-language-model-fine-tuning-with","slug":"universal-language-model-fine-tuning-with","title":"Universal Language Model Fine-Tuning with Subword Tokenization for Polish","date":"2018-10-24","arxiv_id":"1810.10222","repositories_listed":2,"syntology":null},{"url":"/paper/continual-learning-of-recurrent-neural","slug":"continual-learning-of-recurrent-neural","title":"Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations","date":"2018-10-17","arxiv_id":"1810.07411","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/continual-learning-of-recurrent-neural#ran","syntology_url":"https://syntology.ai/paper/1810.07411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.07411"}},"official":{"repos":["AnkurMali/ContinualPTNCN"],"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/structured-content-preservation-for","slug":"structured-content-preservation-for","title":"Structured Content Preservation for Unsupervised Text Style Transfer","date":"2018-10-15","arxiv_id":"1810.06526","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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) · 0 unverified","sample_list":"/paper/structured-content-preservation-for#ran","syntology_url":"https://syntology.ai/paper/1810.06526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.06526"}},"official":{"repos":["YouzhiTian/Structured-Content-Preservation-for-Unsupervised-Text-Style-Transfer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/frage-frequency-agnostic-word-representation","slug":"frage-frequency-agnostic-word-representation","title":"FRAGE: Frequency-Agnostic Word Representation","date":"2018-09-18","arxiv_id":"1809.06858","repositories_listed":2,"syntology":null},{"url":"/paper/context-free-transductions-with-neural-stacks","slug":"context-free-transductions-with-neural-stacks","title":"Context-Free Transductions with Neural Stacks","date":"2018-09-08","arxiv_id":"1809.02836","repositories_listed":2,"syntology":null},{"url":"/paper/pyramidal-recurrent-unit-for-language","slug":"pyramidal-recurrent-unit-for-language","title":"Pyramidal Recurrent Unit for Language Modeling","date":"2018-08-27","arxiv_id":"1808.09029","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/pyramidal-recurrent-unit-for-language#ran","syntology_url":"https://syntology.ai/paper/1808.09029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.09029"}},"official":{"repos":["sacmehta/PRU"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarially-regularising-neural-nli-models","slug":"adversarially-regularising-neural-nli-models","title":"Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge","date":"2018-08-26","arxiv_id":"1808.08609","repositories_listed":2,"syntology":null},{"url":"/paper/relational-recurrent-neural-networks","slug":"relational-recurrent-neural-networks","title":"Relational recurrent neural networks","date":"2018-06-05","arxiv_id":"1806.01822","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/relational-recurrent-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1806.01822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01822"}},"official":null}},{"url":"/paper/contextual-augmentation-data-augmentation-by","slug":"contextual-augmentation-data-augmentation-by","title":"Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations","date":"2018-05-16","arxiv_id":"1805.06201","repositories_listed":2,"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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/contextual-augmentation-data-augmentation-by#ran","syntology_url":"https://syntology.ai/paper/1805.06201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.06201"}},"official":{"repos":["pfnet-research/contextual_augmentation"],"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/building-language-models-for-text-with-named","slug":"building-language-models-for-text-with-named","title":"Building Language Models for Text with Named Entities","date":"2018-05-13","arxiv_id":"1805.04836","repositories_listed":2,"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/building-language-models-for-text-with-named#ran","syntology_url":"https://syntology.ai/paper/1805.04836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.04836"}},"official":{"repos":["uclanlp/NamedEntityLanguageModel"],"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/subword-regularization-improving-neural","slug":"subword-regularization-improving-neural","title":"Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates","date":"2018-04-29","arxiv_id":"1804.10959","repositories_listed":2,"syntology":null},{"url":"/paper/colorless-green-recurrent-networks-dream","slug":"colorless-green-recurrent-networks-dream","title":"Colorless green recurrent networks dream hierarchically","date":"2018-03-29","arxiv_id":"1803.11138","repositories_listed":2,"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":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/colorless-green-recurrent-networks-dream#ran","syntology_url":"https://syntology.ai/paper/1803.11138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.11138"}},"official":{"repos":["facebookresearch/colorlessgreenRNNs"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/network-traffic-anomaly-detection-using","slug":"network-traffic-anomaly-detection-using","title":"Network Traffic Anomaly Detection Using Recurrent Neural Networks","date":"2018-03-28","arxiv_id":"1803.10769","repositories_listed":2,"syntology":null},{"url":"/paper/polisis-automated-analysis-and-presentation","slug":"polisis-automated-analysis-and-presentation","title":"Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning","date":"2018-02-07","arxiv_id":"1802.02561","repositories_listed":2,"syntology":null},{"url":"/paper/discrete-autoencoders-for-sequence-models","slug":"discrete-autoencoders-for-sequence-models","title":"Discrete Autoencoders for Sequence Models","date":"2018-01-29","arxiv_id":"1801.09797","repositories_listed":2,"syntology":null},{"url":"/paper/training-rnns-as-fast-as-cnns","slug":"training-rnns-as-fast-as-cnns","title":"Training RNNs as Fast as CNNs","date":"2018-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/letter-based-speech-recognition-with-gated","slug":"letter-based-speech-recognition-with-gated","title":"Letter-Based Speech Recognition with Gated ConvNets","date":"2017-12-22","arxiv_id":"1712.09444","repositories_listed":2,"syntology":null},{"url":"/paper/effective-use-of-bidirectional-language","slug":"effective-use-of-bidirectional-language","title":"Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition","date":"2017-11-21","arxiv_id":"1711.07908","repositories_listed":2,"syntology":null},{"url":"/paper/unbounded-cache-model-for-online-language","slug":"unbounded-cache-model-for-online-language","title":"Unbounded cache model for online language modeling with open vocabulary","date":"2017-11-07","arxiv_id":"1711.02604","repositories_listed":2,"syntology":null},{"url":"/paper/rotational-unit-of-memory","slug":"rotational-unit-of-memory","title":"Rotational Unit of Memory","date":"2017-10-26","arxiv_id":"1710.09537","repositories_listed":2,"syntology":null},{"url":"/paper/dynamic-entity-representations-in-neural","slug":"dynamic-entity-representations-in-neural","title":"Dynamic Entity Representations in Neural Language Models","date":"2017-08-02","arxiv_id":"1708.00781","repositories_listed":2,"syntology":null},{"url":"/paper/bayesian-sparsification-of-recurrent-neural","slug":"bayesian-sparsification-of-recurrent-neural","title":"Bayesian Sparsification of Recurrent Neural Networks","date":"2017-07-31","arxiv_id":"1708.00077","repositories_listed":2,"syntology":null},{"url":"/paper/dual-rectified-linear-units-drelus-a","slug":"dual-rectified-linear-units-drelus-a","title":"Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks","date":"2017-07-25","arxiv_id":"1707.08214","repositories_listed":2,"syntology":null}],"record_sha256":"752332b3dfadf986c3751f7cdf0daaf2576ceec72fc73f7a295d85204784fb0a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}