Extracting relations across large text spans has been relatively underexplored in NLP, but it is particularly important for high-value domains such as biomedicine, where obtaining high recall of the latest findings is crucial for practical applications. Compared to conventional information extraction confined to short text spans, document-level relation extraction faces additional challenges in both inference and learning. Given longer text spans, state-of-the-art neural architectures are less effective and task-specific self-supervision such as distant supervision becomes very noisy. In this paper, we propose decomposing document-level relation extraction into relation detection and argument resolution, taking inspiration from Davidsonian semantics. This enables us to incorporate explicit discourse modeling and leverage modular self-supervision for each sub-problem, which is less noise-prone and can be further refined end-to-end via variational EM. We conduct a thorough evaluation in biomedical machine reading for precision oncology, where cross-paragraph relation mentions are prevalent. Our method outperforms prior state of the art, such as multi-scale learning and graph neural networks, by over 20 absolute F1 points. The gain is particularly pronounced among the most challenging relation instances whose arguments never co-occur in a paragraph.<\/p>\n","protected":false},"excerpt":{"rendered":"
Extracting relations across large text spans has been relatively underexplored in NLP, but it is particularly important for high-value domains such as biomedicine, where obtaining high recall of the latest findings is crucial for practical applications. Compared to conventional information extraction confined to short text spans, document-level relation extraction faces additional challenges in both inference […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13545,13553],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[260464],"msr-conference":[260143],"msr-journal":[],"msr-impact-theme":[261673],"msr-pillar":[],"class_list":["post-784804","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-language-technologies","msr-research-area-medical-health-genomics","msr-locale-en_us","msr-field-of-study-natural-langage-processing"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2021-9-11","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"http:\/\/export.arxiv.org\/pdf\/2109.05362","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/pdf\/2109.05362.pdf","label_id":"243132","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Sheng Zhang","user_id":39087,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Sheng Zhang"},{"type":"user_nicename","value":"Cliff Wong","user_id":38508,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Cliff Wong"},{"type":"user_nicename","value":"Naoto Usuyama","user_id":38670,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Naoto Usuyama"},{"type":"guest","value":"sarthak-jain","user_id":721069,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=sarthak-jain"},{"type":"user_nicename","value":"Tristan Naumann","user_id":37929,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Tristan Naumann"},{"type":"user_nicename","value":"Hoifung Poon","user_id":32016,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Hoifung Poon"}],"msr_impact_theme":["Health"],"msr_research_lab":[199565,849856],"msr_event":[760690],"msr_group":[952050],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/784804"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/784804\/revisions"}],"predecessor-version":[{"id":789743,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/784804\/revisions\/789743"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=784804"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=784804"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=784804"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=784804"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=784804"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=784804"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=784804"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=784804"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=784804"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=784804"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=784804"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=784804"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=784804"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=784804"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=784804"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=784804"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}