國立虎尾科技大學 |

Exploiting Linguistic Knowledge in Lexical and Compositional Semantic Models.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Exploiting Linguistic Knowledge in Lexical and Compositional Semantic Models./
作者:	Wang, Tong.
面頁冊數:	1 online resource (153 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781369854572

Exploiting Linguistic Knowledge in Lexical and Compositional Semantic Models.
Wang, Tong.

Exploiting Linguistic Knowledge in Lexical and Compositional Semantic Models. - 1 online resource (153 pages)

Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.

Thesis (Ph.D.)--University of Toronto (Canada), 2016.

Includes bibliographical references

A fundamental principle in distributional semantic models is to use similarity in linguistic environment as a proxy for similarity in meaning. Known as the distributional hypothesis, the principle has been successfully applied to many areas in natural language processing. As a proxy, however, it also suffers from critical limitations and exceptions, many of which are the result of the overly simplistic definitions of the linguistic environment. In this thesis, I hypothesize that the quality of distributional models can be improved by carefully incorporating linguistic knowledge into the definition of linguistic environment.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369854572Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Exploiting Linguistic Knowledge in Lexical and Compositional Semantic Models.
LDR:03635ntm a2200349K 4500 001 913666
005 20180622095235.5
006 m o u
007 cr mn||||a|a||
008 190606s2016 xx obm 000 0 eng d
020 $a 9781369854572
035 $a (MiAaPQ)AAI10195472
035 $a (MiAaPQ)toronto:14973
035 $a AAI10195472
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Wang, Tong. $3 1179592
245 1 0 $a Exploiting Linguistic Knowledge in Lexical and Compositional Semantic Models.
264 0 $c 2016
300 $a 1 online resource (153 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
500 $a Adviser: Graeme Hirst.
502 $a Thesis (Ph.D.)--University of Toronto (Canada), 2016.
504 $a Includes bibliographical references
520 $a A fundamental principle in distributional semantic models is to use similarity in linguistic environment as a proxy for similarity in meaning. Known as the distributional hypothesis, the principle has been successfully applied to many areas in natural language processing. As a proxy, however, it also suffers from critical limitations and exceptions, many of which are the result of the overly simplistic definitions of the linguistic environment. In this thesis, I hypothesize that the quality of distributional models can be improved by carefully incorporating linguistic knowledge into the definition of linguistic environment.
520 $a The hypothesis is validated in the context of three closely related semantic relations, namely near-synonymy, lexical similarity, and polysemy. On the lexical level, the definition of linguistic environment is examined under three different distributional frameworks including lexical co-occurrence, syntactic and lexicographic dependency, and taxonomic structures. Firstly, combining kernel methods and lexical level co-occurrence with matrix factorization is shown to be highly effective in capturing the fine-grained nuances among near-synonyms. Secondly, syntactic and lexicographic information is shown to result in notable improvement in lexical embedding learning when evaluated in lexical similarity benchmarks. Thirdly, for taxonomy-based measures of lexical similarity, the intuitions for using structural features such as depth and density are examined and challenged, and the refined definitions are shown to improve correlation between the features and human judgements of similarity as well as performances of similarity measures using these features.
520 $a On the compositional level, distributional models of multi-word contexts are also shown to benefit from incorporating syntactic and lexicographic knowledge. Analytically, the use of syntactic teacher-forcing is motivated by derivations of full gradients in long short-term memory units in recurrent neural networks. Empirically, syntactic knowledge helps achieve statistically significant improvement in language modelling and state-of-the-art accuracy in near-synonym lexical choice. Finally, a compositional similarity function is developed to measure the similarity between two sets of random events. Application in polysemy with lexicographic knowledge produces state-of-the-art performance in unsupervised word sense disambiguation.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Toronto (Canada). $b Computer Science. $3 845521
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10195472 $z click for full text (PQDT)