{"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/discourse-segmentation","name":"Discourse Segmentation","slug":"discourse-segmentation","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":38,"papers_with_code":14,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/gum","name":"GUM","full_name":"Georgetown University Multilayer corpus","num_papers_in_archive":13},{"url":"/dataset/amalgum","name":"AMALGUM","full_name":"A Machine Annotated Lookalike of GUM","num_papers_in_archive":5},{"url":"/dataset/disrpt2019","name":"DISRPT2019","full_name":"DISRPT2019 shared task on Discourse Unit Segmentation and Connective Detection","num_papers_in_archive":4},{"url":"/dataset/disrpt2021","name":"DISRPT2021","full_name":"DISRPT2021 shared task on Discourse Unit Segmentation, Connective Detection and Discourse Relation Classification","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/discourse-parsing","name":"Discourse Parsing"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":38,"of":38,"of_with_code":14,"tagged_in_all":38,"counts":{"archive_papers_tagged":38,"with_a_code_link":14,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":38,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":2,"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"},"items":[{"url":"/paper/two-pass-discourse-segmentation-with-pairing","slug":"two-pass-discourse-segmentation-with-pairing","title":"Two-pass Discourse Segmentation with Pairing and Global Features","date":"2014-07-30","arxiv_id":"1407.8215","repositories_listed":4,"syntology":null},{"url":"/paper/open-retrieval-conversational-machine-reading","slug":"open-retrieval-conversational-machine-reading","title":"Open-Retrieval Conversational Machine Reading","date":"2021-02-17","arxiv_id":"2102.08633","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/open-retrieval-conversational-machine-reading#ran","syntology_url":"https://syntology.ai/paper/2102.08633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.08633"}},"official":{"repos":["yifan-gao/open_retrieval_conversational_machine_reading"],"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":["listed","unlocated"]}}},{"url":"/paper/weakly-supervised-discourse-segmentation-for","slug":"weakly-supervised-discourse-segmentation-for","title":"Weakly supervised discourse segmentation for multiparty oral conversations","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dmrst-a-joint-framework-for-document-level","slug":"dmrst-a-joint-framework-for-document-level","title":"DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing","date":"2021-10-09","arxiv_id":"2110.04518","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":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/dmrst-a-joint-framework-for-document-level#ran","syntology_url":"https://syntology.ai/paper/2110.04518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04518"}},"official":{"repos":["seq-to-mind/DMRST_Parser"],"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/discodisco-at-the-disrpt2021-shared-task-a","slug":"discodisco-at-the-disrpt2021-shared-task-a","title":"DisCoDisCo at the DISRPT2021 Shared Task: A System for Discourse Segmentation, Classification, and Connective Detection","date":"2021-09-20","arxiv_id":"2109.09777","repositories_listed":1,"syntology":null},{"url":"/paper/rst-parsing-from-scratch","slug":"rst-parsing-from-scratch","title":"RST Parsing from Scratch","date":"2021-05-23","arxiv_id":"2105.10861","repositories_listed":1,"syntology":null},{"url":"/paper/discern-discourse-aware-entailment-reasoning","slug":"discern-discourse-aware-entailment-reasoning","title":"Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading","date":"2020-10-05","arxiv_id":"2010.01838","repositories_listed":1,"syntology":null},{"url":"/paper/joint-learning-of-syntactic-features-helps","slug":"joint-learning-of-syntactic-features-helps","title":"Joint Learning of Syntactic Features Helps Discourse Segmentation","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/text-segmentation-by-cross-segment-attention","slug":"text-segmentation-by-cross-segment-attention","title":"Text Segmentation by Cross Segment Attention","date":"2020-04-30","arxiv_id":"2004.14535","repositories_listed":1,"syntology":null},{"url":"/paper/gumdrop-at-the-disrpt2019-shared-task-a-model","slug":"gumdrop-at-the-disrpt2019-shared-task-a-model","title":"GumDrop at the DISRPT2019 Shared Task: A Model Stacking Approach to Discourse Unit Segmentation and Connective Detection","date":"2019-04-23","arxiv_id":"1904.10419","repositories_listed":1,"syntology":null},{"url":"/paper/from-news-to-medical-cross-domain-discourse","slug":"from-news-to-medical-cross-domain-discourse","title":"From News to Medical: Cross-domain Discourse Segmentation","date":"2019-04-14","arxiv_id":"1904.06682","repositories_listed":1,"syntology":null},{"url":"/paper/toward-fast-and-accurate-neural-discourse","slug":"toward-fast-and-accurate-neural-discourse","title":"Toward Fast and Accurate Neural Discourse Segmentation","date":"2018-08-28","arxiv_id":"1808.09147","repositories_listed":1,"syntology":null},{"url":"/paper/does-syntax-help-discourse-segmentation-not","slug":"does-syntax-help-discourse-segmentation-not","title":"Does syntax help discourse segmentation? Not so much","date":"2017-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-and-cross-domain-discourse-1","slug":"cross-lingual-and-cross-domain-discourse-1","title":"Cross-lingual and cross-domain discourse segmentation of entire documents","date":"2017-04-13","arxiv_id":"1704.04100","repositories_listed":1,"syntology":null},{"url":null,"slug":"automatic-alignment-of-discourse-relations-of","title":"Automatic Alignment of Discourse Relations of Different Discourse Annotation Frameworks","date":"2024-03-29","arxiv_id":"2403.20196","repositories_listed":0,"syntology":null},{"url":null,"slug":"discourse-relations-classification-and-cross","title":"Discourse Relations Classification and Cross-Framework Discourse Relation Classification Through the Lens of Cognitive Dimensions: An Empirical Investigation","date":"2023-11-01","arxiv_id":"2311.00451","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentence-level-discourse-parsing-as-text-to","title":"Sentence-Level Discourse Parsing as Text-to-Text Generation","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-language-model-based-generative-classifier","title":"A Language Model-based Generative Classifier for Sentence-level Discourse Parsing","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-transformer-based-approach-towards","title":"A Transformer Based Approach towards Identification of Discourse Unit Segments and Connectives","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"delexicalised-multilingual-discourse","title":"Delexicalised Multilingual Discourse Segmentation for DISRPT 2021 and Tense, Mood, Voice and Modality Tagging for 11 Languages","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-lingual-discourse-segmentation-and","title":"Multi-lingual Discourse Segmentation and Connective Identification: MELODI at Disrpt2021","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-conditional-splitting-framework-for","title":"A Conditional Splitting Framework for Efficient Constituency Parsing","date":"2021-06-30","arxiv_id":"2106.15760","repositories_listed":0,"syntology":null},{"url":null,"slug":"discourse-based-argument-segmentation-and","title":"Discourse-based Argument Segmentation and Annotation","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-discourse-analysis-for-generating","title":"Deep Discourse Analysis for Generating Personalized Feedback in Intelligent Tutor Systems","date":"2021-03-13","arxiv_id":"2103.07785","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-discourse-segmentation-review-and","title":"Automatic Discourse Segmentation: Review and Perspectives","date":"2020-05-01","arxiv_id":"2005.00468","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-discourse-segmentation-an","title":"Automatic Discourse Segmentation: an evaluation in French","date":"2020-02-10","arxiv_id":"2002.04095","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-lingual-and-cross-genre-discourse-unit","title":"Multi-lingual and Cross-genre Discourse Unit Segmentation","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-segmentation-based-on-neural","title":"Multilingual segmentation based on neural networks and pre-trained word embeddings","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tony-contextual-embeddings-for-accurate","title":"ToNy: Contextual embeddings for accurate multilingual discourse segmentation of full documents","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"chinese-discourse-segmentation-using","title":"Chinese Discourse Segmentation Using Bilingual Discourse Commonality","date":"2018-08-30","arxiv_id":"1809.01497","repositories_listed":0,"syntology":null},{"url":null,"slug":"discourse-segmentation-for-building-a-rst","title":"Discourse Segmentation for Building a RST Chinese Treebank","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-and-cross-domain-discourse","title":"Cross-lingual and cross-domain discourse segmentation of entire documents","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extending-automatic-discourse-segmentation","title":"Extending Automatic Discourse Segmentation for Texts in Spanish to Catalan","date":"2017-03-11","arxiv_id":"1703.04718","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-corpus-based-approach-for-spanish-chinese","title":"A Corpus-based Approach for Spanish-Chinese Language Learning","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"estimation-of-discourse-segmentation-labels","title":"Estimation of Discourse Segmentation Labels from Crowd Data","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"segmentation-evaluation-metrics-a-comparison","title":"Segmentation evaluation metrics, a comparison grounded on prosodic and discourse units","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reranking-model-for-discourse-segmentation","title":"A Reranking Model for Discourse Segmentation using Subtree Features","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"clause-based-discourse-segmentation-of-arabic","title":"Clause-based Discourse Segmentation of Arabic Texts","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/task/discourse-segmentation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/discourse-segmentation/papers/ran/1","json":"/task/discourse-segmentation/papers/ran/1.json","rows":2}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"8ead925966d35f10cc6ce4c802200e2f8cabbdfc66be1f1e7b7a357bf56e1db2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}