Date & Time: Friday, 13 October 15:10-16:40
\nPlace: AI,Inc. Seminar Hall[L1]\uff08IS\uff09and Online(webex)
\nLanguage: Japanese<\/p>\n
Lecturer: Daichi Mochihashi (Associate Professor, The Institute of Statistical Mathematics)<\/p>\n
Title: Holographic CCG Parsing<\/p>\n
Abstract:
\nWe propose a method for formulating CCG as a recursive composition in a continuous vector space. Recent CCG supertagging and parsing models generally demonstrate high performance, yet rely on black-box neural architectures to implicitly model phrase structure dependencies.
\nInstead, we leverage the method of holographic embeddings (Nickel et al., 2016) as a compositional operator to explicitly model the dependencies between words and phrase structures in the embedding space. Experimental results revealed that holographic composition effectively improves the supertagging accuracy to achieve state-of-the-art parsing performance when using a C&C parser. The proposed span-based parsing algorithm using holographic composition achieves performance comparable to state-of-the-art neural parsing with Transformers. Furthermore, our model can semantically and syntactically infill text at the phrase level due to the decomposability of holographic composition.<\/p>\n
References:
\n“Holographic CCG Parsing”. Ryosuke Yamaki, Tadahiro Taniguchi, Daichi Mochihashi.
\nACL 2023, pp.262-276, 2023. (Long, Oral)
\nhttp:\/\/chasen.org\/~daiti-m\/paper\/yamaki23holccg.pdf<\/p>\n
<\/p>\n
<\/p>\n
<\/p>\n
<\/p>\n","protected":false},"excerpt":{"rendered":"
Date & Time: Friday, 13 October 15:10-16:40 Place: AI,Inc. Seminar Hall[L1]\uff08IS\uff09and Online(webex) Language: Japanese Lecturer: Daichi Mochihashi (Associate Professor, The Institute of Statistical Mathematics) Title: Holographic CCG Parsing Abstract: We propose a method for formulating CCG as a recursive composition in a continuous vector space. Recent CCG supertagging and parsing models generally demonstrate high performance, […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_locale":"en_US","_original_post":"http:\/\/www-dsc.naist.jp\/dsc_naist\/?p=5290","_links_to":"","_links_to_target":""},"categories":[3],"tags":[],"event_taxonomy":[14,23],"acf":[],"_links":{"self":[{"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts\/5294"}],"collection":[{"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/comments?post=5294"}],"version-history":[{"count":1,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts\/5294\/revisions"}],"predecessor-version":[{"id":5295,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts\/5294\/revisions\/5295"}],"wp:attachment":[{"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/media?parent=5294"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/categories?post=5294"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/tags?post=5294"},{"taxonomy":"event_taxonomy","embeddable":true,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/event_taxonomy?post=5294"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}