\n
\nDiscourse models capture relations across different sentences in a document.
\nThese models are crucial in applications where it is important to generate
\ncoherent text. Traditionally, rule-based approaches have been predominant in
\ndiscourse research. However, these models are hard to incorporate as-is in
\nmodern systems: they rely on handcrafted rules, valid only for limited domains,
\nwith no guarantee of scalability or portability.<\/P><\/p>\n
In this talk, I will present discourse models that can be effectively learned
\nfrom a collection of unannotated texts. The key premise of our work is that the
\ndistribution of entities in coherent texts exhibits certain regularities. The
\nmodels I will be presenting operate over an automatically-computed
\nrepresentation that reflects distributional, syntactic, and referential
\ninformation about discourse entities. This representation allows us to induce
\nthe properties of coherent texts from a given corpus, without recourse to manual
\nannotation or a predefined knowledge base. To conclude my talk, I will
\nshow how these models can be effectively integrated in statistical generation
\nand summarization systems.<\/P><\/p>\n
This is joint work with Mirella Lapata and Lillian Lee.<\/P>\n<\/p><\/blockquote>\n","protected":false},"excerpt":{"rendered":"
The Language @MIT series returns this week, featuring a talk by Regina Barzilay. Title: Learning to Model Text Structure Speaker: Regina Barzilay, CSAIL When: Wednesday Dec 3, 3-4:30pm Where: 26-310 Discourse models capture relations across different sentences in a document. These models are crucial in applications where it is important to generate coherent text. Traditionally, […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-322","post","type-post","status-publish","format-standard","hentry","category-talks"],"_links":{"self":[{"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts\/322","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/comments?post=322"}],"version-history":[{"count":4,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts\/322\/revisions"}],"predecessor-version":[{"id":384,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts\/322\/revisions\/384"}],"wp:attachment":[{"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/media?parent=322"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/categories?post=322"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/tags?post=322"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}