This week’s seminar is organized as follows:
1. The seminar time is 1.pm, Wed<\/strong>, at Zhongguancun Technology Park ,Building 5, 1306.
2. The lecturer is Zhaoyang Wang<\/strong>, the paper’s title is Deep contextualized word representations<\/strong>.
3. The seminar will be hosted by Li Shen.
4. Attachment is the paper of this seminar, please download in advance. <\/p>\n\n\n\n

\n\t
\n\t\tDeep contextualized word representations\n\t<\/p>\n\t
\n\t\tMatthew E.\nPetersy, Mark Neumanny, Mohit Iyyery, Matt Gardnery,\n\t<\/p>\n\t
\n\t\tChristopher Clark,\nKenton Lee, Luke Zettlemoyery\n\t<\/p>\n\t
\n\t\tAbstract\n\t<\/p>\n\t
\n\t\t We introduce a new type of deep\ncontextualized word representation that models both (1) complex characteristics\nof word use (e.g., syntax and semantics), and (2) how these uses vary across\nlinguistic contexts (i.e., to model polysemy). Our word vectors are learned\nfunctions of the internal states of a deep bidirectional language model (biLM),\nwhich is pretrained on a large text corpus. We show that these representations\ncan be easily added to existing models and significantly improve the state of\nthe art across six challenging NLP problems, including question answering,\ntextual entailment and sentiment analysis. We also present an analysis showing\nthat exposing the deep internals of the pre-trained network is crucial,\nallowing downstream models to mix different types of semi-supervision signals.<\/span>\n\t<\/p>\n<\/div>\n\n\n\n\n\n\n\n
NLPIR SEMINAR 12th ISSUE COMPLETED<\/strong><\/h2>\n\n\n\n
Last week, Zhaoyang Wang gave a\npresentation about the paper, Deep contextualized word representations, and\nshared some opinion on it.<\/p>\n\n\n\n
$\"\"$ <\/figure>\n\n\n\n
After the presentation, Professor Zhang\nasked that how ELMo solve problems. What’s the difference?<\/p>\n\n\n\n
Zhaoyang\u2019s answer: This paper uses\ndifferent model in different context. Each layer has its own weight.<\/p>\n\n\n\n
The powerpoint of the presentation can be download.<\/p>\n\n\n\n
Deep contextualized word representations<\/a>\u4e0b\u8f7d<\/a><\/div>\n","protected":false},"excerpt":{"rendered":"
NLPIR SEMINAR Y2018#12 INTRO\ufeff &nbs … \u7ee7\u7eed\u9605\u8bfb →<\/span><\/a><\/p>\n","protected":false},"author":862,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[37,38],"tags":[],"_links":{"self":[{"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/posts\/6216"}],"collection":[{"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/users\/862"}],"replies":[{"embeddable":true,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/comments?post=6216"}],"version-history":[{"count":3,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/posts\/6216\/revisions"}],"predecessor-version":[{"id":6223,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/posts\/6216\/revisions\/6223"}],"wp:attachment":[{"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/media?parent=6216"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/categories?post=6216"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/tags?post=6216"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

NLPIR SEMINAR Y2018#12<\/h2>\n\n\n\n