{"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/exploring-neural-methods-for-parsing","title":"Exploring Neural Methods for Parsing Discourse Representation Structures","arxiv_id":"1810.12579","date":"2018-10-30","proceeding":"TACL 2018 1","authors":["Rik van Noord","Lasha Abzianidze","Antonio Toral","Johan Bos"],"abstract":"Neural methods have had several recent successes in semantic parsing, though\nthey have yet to face the challenge of producing meaning representations based\non formal semantics. We present a sequence-to-sequence neural semantic parser\nthat is able to produce Discourse Representation Structures (DRSs) for English\nsentences with high accuracy, outperforming traditional DRS parsers. To\nfacilitate the learning of the output, we represent DRSs as a sequence of flat\nclauses and introduce a method to verify that produced DRSs are well-formed and\ninterpretable. We compare models using characters and words as input and see\n(somewhat surprisingly) that the former performs better than the latter. We\nshow that eliminating variable names from the output using De Bruijn-indices\nincreases parser performance. Adding silver training data boosts performance\neven further.","url_abs":"http://arxiv.org/abs/1810.12579v1","url_pdf":"http://arxiv.org/pdf/1810.12579v1.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":"exploring-neural-methods-for-parsing","repo_url":"https://github.com/RikVN/Neural_DRS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"drs-parsing","task_name":"DRS Parsing"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/drs-parsing-on-pmb-2-2-0","task":"DRS Parsing","dataset":"PMB-2.2.0","model":"Character-level bi-LSTM seq2seq","rank_in_archive_order":4,"of":6,"metrics":{"F1":"83.3"},"uses_additional_data":false},{"leaderboard":"/sota/drs-parsing-on-pmb-3-0-0","task":"DRS Parsing","dataset":"PMB-3.0.0","model":"Character-level bi-LSTM seq2seq","rank_in_archive_order":3,"of":3,"metrics":{"F1":"84.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.12579","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}