{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/a-deep-sequential-model-for-discourse-parsing","title":"A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues","arxiv_id":"1812.00176","date":"2018-12-01","proceeding":null,"authors":["Zhouxing Shi","Minlie Huang"],"abstract":"Discourse structures are beneficial for various NLP tasks such as dialogue\nunderstanding, question answering, sentiment analysis, and so on. This paper\npresents a deep sequential model for parsing discourse dependency structures of\nmulti-party dialogues. The proposed model aims to construct a discourse\ndependency tree by predicting dependency relations and constructing the\ndiscourse structure jointly and alternately. It makes a sequential scan of the\nElementary Discourse Units (EDUs) in a dialogue. For each EDU, the model\ndecides to which previous EDU the current one should link and what the\ncorresponding relation type is. The predicted link and relation type are then\nused to build the discourse structure incrementally with a structured encoder.\nDuring link prediction and relation classification, the model utilizes not only\nlocal information that represents the concerned EDUs, but also global\ninformation that encodes the EDU sequence and the discourse structure that is\nalready built at the current step. Experiments show that the proposed model\noutperforms all the state-of-the-art baselines.","url_abs":"http://arxiv.org/abs/1812.00176v1","url_pdf":"http://arxiv.org/pdf/1812.00176v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-deep-sequential-model-for-discourse-parsing","repo_url":"https://github.com/shizhouxing/DialogueDiscourseParsing","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"discourse-parsing","task_name":"Discourse Parsing"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/discourse-parsing-on-stac","task":"Discourse Parsing","dataset":"STAC","model":"Deep Sequential","rank_in_archive_order":6,"of":7,"metrics":{"Link & Rel F1":"55.7","Link F1":"73.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.00176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00176"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shizhouxing/DialogueDiscourseParsing","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f965e9e04d49783f","entry":"dropout","repo":"shizhouxing/DialogueDiscourseParsing","repo_kind":"official","path":"libs/dropout.py","file_url":"https://github.com/shizhouxing/DialogueDiscourseParsing/blob/HEAD/libs/dropout.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f965e9e04d49783f"}},{"code_sha256_prefix":"a8dc7d1b5d584c44","entry":"load_scip_output","repo":"shizhouxing/DialogueDiscourseParsing","repo_kind":"official","path":"baseline/ilp.py","file_url":"https://github.com/shizhouxing/DialogueDiscourseParsing/blob/HEAD/baseline/ilp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a8dc7d1b5d584c44"}},{"code_sha256_prefix":"ccadce9c5675ef2d","entry":"mk_zimpl_input","repo":"shizhouxing/DialogueDiscourseParsing","repo_kind":"official","path":"baseline/ilp.py","file_url":"https://github.com/shizhouxing/DialogueDiscourseParsing/blob/HEAD/baseline/ilp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ccadce9c5675ef2d"}},{"code_sha256_prefix":"472d921a184182ab","entry":"pretty_data","repo":"shizhouxing/DialogueDiscourseParsing","repo_kind":"official","path":"baseline/ilp.py","file_url":"https://github.com/shizhouxing/DialogueDiscourseParsing/blob/HEAD/baseline/ilp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"472d921a184182ab"}},{"code_sha256_prefix":"c785443e1a808b50","entry":"process_dialogue","repo":"shizhouxing/DialogueDiscourseParsing","repo_kind":"official","path":"data_pre.py","file_url":"https://github.com/shizhouxing/DialogueDiscourseParsing/blob/HEAD/data_pre.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c785443e1a808b50"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}