{"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/generalizing-natural-language-analysis-1","title":"Generalizing Natural Language Analysis through Span-relation Representations","arxiv_id":"1911.03822","date":"2019-11-10","proceeding":"ACL 2020 6","authors":["Zhengbao Jiang","Wei Xu","Jun Araki","Graham Neubig"],"abstract":"Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple insight that a great variety of tasks can be represented in a single unified format consisting of labeling spans and relations between spans, thus a single task-independent model can be used across different tasks. We perform extensive experiments to test this insight on 10 disparate tasks spanning dependency parsing (syntax), semantic role labeling (semantics), relation extraction (information content), aspect based sentiment analysis (sentiment), and many others, achieving performance comparable to state-of-the-art specialized models. We further demonstrate benefits of multi-task learning, and also show that the proposed method makes it easy to analyze differences and similarities in how the model handles different tasks. Finally, we convert these datasets into a unified format to build a benchmark, which provides a holistic testbed for evaluating future models for generalized natural language analysis.","url_abs":"https://arxiv.org/abs/1911.03822v2","url_pdf":"https://arxiv.org/pdf/1911.03822v2.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":"generalizing-natural-language-analysis-1","repo_url":"https://github.com/neulab/cmu-multinlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"generalizing-natural-language-analysis-1","repo_url":"https://github.com/jzbjyb/SpanRel","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generalizing-natural-language-analysis-1","repo_url":"https://github.com/jiachengli1995/jointie","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"aspect-based-sentiment-analysis-1","task_name":"Aspect-Based Sentiment Analysis"},{"task_slug":"aspect-based-sentiment-analysis","task_name":"Aspect-Based Sentiment Analysis (ABSA)"},{"task_slug":"constituency-parsing","task_name":"Constituency Parsing"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"part-of-speech-tagging","task_name":"Part-Of-Speech Tagging"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"semantic-role-labeling","task_name":"Semantic Role Labeling"},{"task_slug":"semantic-role-labeling-predicted-predicates","task_name":"Semantic Role Labeling (predicted predicates)"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/constituency-parsing-on-penn-treebank","task":"Constituency Parsing","dataset":"Penn Treebank","model":"SpanRel","rank_in_archive_order":13,"of":27,"metrics":{"F1 score":"95.5"},"uses_additional_data":false},{"leaderboard":"/sota/dependency-parsing-on-penn-treebank","task":"Dependency Parsing","dataset":"Penn Treebank","model":"SpanRel","rank_in_archive_order":9,"of":22,"metrics":{"LAS":"94.70","UAS":"96.44"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-conll-2003","task":"Named Entity Recognition (NER)","dataset":"CoNLL 2003 (English)","model":"SpanRel","rank_in_archive_order":48,"of":73,"metrics":{"F1":"92.2"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-wlpc","task":"Named Entity Recognition (NER)","dataset":"WLPC","model":"SpanRel","rank_in_archive_order":2,"of":2,"metrics":{"F1":"79.2"},"uses_additional_data":false},{"leaderboard":"/sota/part-of-speech-tagging-on-penn-treebank","task":"Part-Of-Speech Tagging","dataset":"Penn Treebank","model":"SpanRel","rank_in_archive_order":6,"of":20,"metrics":{"Accuracy":"97.7"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-semeval-2010-task-8","task":"Relation Extraction","dataset":"SemEval-2010 Task-8","model":"SpanRel","rank_in_archive_order":23,"of":31,"metrics":{"F1":"87.4"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-wlpc","task":"Relation Extraction","dataset":"WLPC","model":"SpanRel","rank_in_archive_order":1,"of":2,"metrics":{"F1":"65.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-role-labeling-predicted-predicates-1","task":"Semantic Role Labeling (predicted predicates)","dataset":"CoNLL 2012","model":"SpanRel","rank_in_archive_order":5,"of":7,"metrics":{"F1":"82.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.03822","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}