{"id":2187,"date":"2019-01-03T09:50:10","date_gmt":"2019-01-03T09:50:10","guid":{"rendered":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/?p=2187"},"modified":"2019-02-23T09:58:05","modified_gmt":"2019-02-23T09:58:05","slug":"wsdm-2019-paper-on-open-domain-question-answering-is-online-now","status":"publish","type":"post","link":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wsdm-2019-paper-on-open-domain-question-answering-is-online-now\/","title":{"rendered":"WSDM 2019 paper on open-domain question answering online"},"content":{"rendered":"\n<p><em>Learning to transform, combine, and reason in open-domain question answering<\/em> by Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, and&nbsp;Maarten de Rijke is online now <a href=\"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-content\/papercite-data\/pdf\/deghani-learning-2019.pdf\">at this location<\/a>.<\/p>\n\n\n\n<p>Users seek direct answers to complex questions from large open-domain knowledge sources like the Web. Open-domain question answering has become a critical task to be solved for building systems that help address users\u2019 complex information needs. Most open-domain question answering systems use a search engine to retrieve a set of candidate documents, select one or a few of them as context, and then apply reading comprehension models to ex- tract answers. Some questions, however, require taking a broader context into account, e.g., by considering low-ranked documents that are not immediately relevant, combining information from multiple documents, and reasoning over multiple facts from these documents to infer the answer. In this paper, we propose a model based on the Transformer architecture that is able to efficiently operate over a larger set of candidate documents by effectively combining the evidence from these documents during multiple steps of reasoning, while it is robust against noise from low-ranked non-relevant documents included in the set. We use our proposed model, called TraCRNet, on two public open-domain question answering datasets, SearchQA and Quasar-T, and achieve results that meet or exceed the state-of-the-art.<\/p>\n\n\n\n<p>The paper will be presented at WSDM 2019.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Learning to transform, combine, and reason in open-domain question answering by Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, and&nbsp;Maarten de Rijke is online now at this location. Users seek direct answers to complex questions from large open-domain knowledge sources like the Web. Open-domain question answering has become a critical task to be solved for building systems&#8230;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-json\/wp\/v2\/posts\/2187"}],"collection":[{"href":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-json\/wp\/v2\/comments?post=2187"}],"version-history":[{"count":3,"href":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-json\/wp\/v2\/posts\/2187\/revisions"}],"predecessor-version":[{"id":2192,"href":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-json\/wp\/v2\/posts\/2187\/revisions\/2192"}],"wp:attachment":[{"href":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-json\/wp\/v2\/media?parent=2187"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-json\/wp\/v2\/categories?post=2187"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/staff.fnwi.uva.nl\/m.derijke\/wp-json\/wp\/v2\/tags?post=2187"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}