The urgency of mitigating COVID-19 has spawned a large and diverse body of scientific literature that is challenging for researchers to navigate. This explosion of information has stimulated interest in automated tools to help identify useful knowledge. We have pursued the use of methods for extracting diverse forms of mechanism relations from the natural language of scientific papers. We seek to identify concepts in COVID-19 and related literature which represent activities, functions, associations and causal relations, ranging from cellular processes to economic impacts. We formulate a broad, coarse-grained schema targeting mechanism relations between open, free-form entities. Our approach strikes a balance between expressivity and breadth that supports generalization across diverse concepts. We curate a dataset of scientific papers annotated according to our novel schema. Using an information extraction model trained on this new corpus, we construct a knowledge base (KB) of 2M mechanism relations, which we make publicly available. Our model is able to extract relations at an F1 at least twice that of baselines such as open IE or related scientific IE systems. We conduct experiments examining the ability of our system to retrieve relevant information on viral mechanisms of action, and on applications of AI to COVID-19 research. In both cases, our system identifies relevant information from our automatically-constructed knowledge base with high precision.<\/p>\n","protected":false},"excerpt":{"rendered":"
The urgency of mitigating COVID-19 has spawned a large and diverse body of scientific literature that is challenging for researchers to navigate. This explosion of information has stimulated interest in automated tools to help identify useful knowledge. We have pursued the use of methods for extracting diverse forms of mechanism relations from the natural language […]<\/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":[13563,13545,13553],"msr-publication-type":[193724],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[246691,247333,248116,248491,248683,246805,248821,247189],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-750142","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-data-platform-analytics","msr-research-area-human-language-technologies","msr-research-area-medical-health-genomics","msr-locale-en_us","msr-field-of-study-computer-science","msr-field-of-study-coronavirus-disease-2019-covid-19","msr-field-of-study-data-science","msr-field-of-study-information-extraction","msr-field-of-study-knowledge-base","msr-field-of-study-natural-language","msr-field-of-study-schema-psychology","msr-field-of-study-scientific-literature"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2021-3-12","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":"arXiv","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":"https:\/\/arxiv.org\/abs\/2010.03824v2","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/europepmc.org\/article\/PPR\/PPR313878","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Tom Hope","user_id":0,"rest_url":false},{"type":"text","value":"Aida Amini","user_id":0,"rest_url":false},{"type":"text","value":"David Wadden","user_id":0,"rest_url":false},{"type":"text","value":"Madeleine van Zuylen","user_id":0,"rest_url":false},{"type":"text","value":"Sravanthi Parasa","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Eric Horvitz","user_id":32033,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Eric Horvitz"},{"type":"text","value":"Daniel Weld","user_id":0,"rest_url":false},{"type":"text","value":"Roy Schwartz","user_id":0,"rest_url":false},{"type":"text","value":"Hannaneh Hajishirzi","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[740920],"msr_group":[916890],"msr_project":[918240,918255],"publication":[],"video":[],"download":[],"msr_publication_type":"miscellaneous","related_content":{"projects":[{"ID":918240,"post_title":"Prevention & control","post_name":"prevention-control","post_type":"msr-project","post_date":"2023-10-25 20:50:13","post_modified":"2023-10-25 20:50:15","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/prevention-control\/","post_excerpt":"Infectious diseases, including COVID-19, continue to pose a significant public health threat, and identifying new cases and tracking disease trends are crucial for effective prevention and control measures. In recent studies, researchers have used various data sources, such as internet search trends, emergency department visits, and online surveys, to assess the impact of public health interventions and recruit study participants. These studies cover a variety of topics from passive surveillance of SARS-CoV-2 on buses to…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/918240"}]}},{"ID":918255,"post_title":"Global response & information","post_name":"global-response-information","post_type":"msr-project","post_date":"2023-10-25 20:53:06","post_modified":"2023-10-26 14:22:31","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/global-response-information\/","post_excerpt":"The COVID-19 pandemic has affected nearly every aspect of life around the world, from healthcare and economics to diet and social needs. As a result, researchers have turned to a variety of methods to understand the impacts of the pandemic and inform policies and recovery efforts. These methods include analyzing internet search data to track shifts in human needs and dietary interests, using self-supervised learning to improve vertical search in the biomedical literature, and studying…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/918255"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/750142","targetHints":{"allow":["GET"]}}],"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":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/750142\/revisions"}],"predecessor-version":[{"id":750145,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/750142\/revisions\/750145"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=750142"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=750142"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=750142"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=750142"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=750142"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=750142"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=750142"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=750142"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=750142"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=750142"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=750142"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=750142"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=750142"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=750142"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=750142"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=750142"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}