大葉大學圖書館 |

登入

回首頁 到查詢結果 [ subject:"Psychology, Cognitive." ]

Finding meaning: Sense inventories f...

Brown, Susan Windisch.

Finding meaning: Sense inventories for improved word sense disambiguation.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
書名/作者:	Finding meaning: Sense inventories for improved word sense disambiguation.
作者:	Brown, Susan Windisch.
面頁冊數:	147 p.
附註:	Source: Dissertation Abstracts International, Volume: 71-06, Section: A, page: 2032.
Contained By:	Dissertation Abstracts International71-06A.
標題:	Language, Linguistics.
標題:	Psychology, Cognitive.
ISBN:	9781109779721
摘要、提要註:	The deep semantic understanding necessary for complex natural language processing tasks, such as automatic question-answering or text summarization, would benefit from highly accurate word sense disambiguation (WSD). This dissertation investigates what makes an appropriate and effective sense inventory for WSD. Drawing on theories and methodologies from cognitive linguistics, psycholinguistics, and computational linguistics, we address underlying assumptions about sense inventories, investigate factors influencing successful sense annotation, and experiment with the appropriateness of using a lexicon enriched with syntactic and semantic information as a sense inventory for WSD.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3403902

Finding meaning: Sense inventories for improved word sense disambiguation.
Brown, Susan Windisch.

Finding meaning: Sense inventories for improved word sense disambiguation. - 147 p.

Source: Dissertation Abstracts International, Volume: 71-06, Section: A, page: 2032.

Thesis (Ph.D.)--University of Colorado at Boulder, 2010.

The deep semantic understanding necessary for complex natural language processing tasks, such as automatic question-answering or text summarization, would benefit from highly accurate word sense disambiguation (WSD). This dissertation investigates what makes an appropriate and effective sense inventory for WSD. Drawing on theories and methodologies from cognitive linguistics, psycholinguistics, and computational linguistics, we address underlying assumptions about sense inventories, investigate factors influencing successful sense annotation, and experiment with the appropriateness of using a lexicon enriched with syntactic and semantic information as a sense inventory for WSD.

ISBN: 9781109779721Subjects--Topical Terms:

423211
Language, Linguistics.

Finding meaning: Sense inventories for improved word sense disambiguation.
LDR:03234nam 2200361 4500 001 344965
005 20110603092118.5
008 110817s2010 ||||||||||||||||| ||eng d
020 $a 9781109779721
035 $a (UMI)AAI3403902
035 $a AAI3403902
040 $a UMI $c UMI
100 1 $a Brown, Susan Windisch. $3 423318
245 1 0 $a Finding meaning: Sense inventories for improved word sense disambiguation.
300 $a 147 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-06, Section: A, page: 2032.
500 $a Adviser: Martha Palmer.
502 $a Thesis (Ph.D.)--University of Colorado at Boulder, 2010.
520 $a The deep semantic understanding necessary for complex natural language processing tasks, such as automatic question-answering or text summarization, would benefit from highly accurate word sense disambiguation (WSD). This dissertation investigates what makes an appropriate and effective sense inventory for WSD. Drawing on theories and methodologies from cognitive linguistics, psycholinguistics, and computational linguistics, we address underlying assumptions about sense inventories, investigate factors influencing successful sense annotation, and experiment with the appropriateness of using a lexicon enriched with syntactic and semantic information as a sense inventory for WSD.
520 $a A psycholinguistic experiment is presented that investigates how people process polysemous words. The significant facilitation found in processing related senses as compared to unrelated senses supports a model of semantic representation in which related senses are not discrete entities. The results suggest that fine-grained sense inventories may not be necessary for WSD, as little information may be lost from using more general senses. It also suggests that flexible sense inventories, in which systems can move between more or less nuanced senses, may improve the portability of WSD systems.
520 $a A series of annotation experiments investigates the factors that affect the reliability of word sense annotation, an important question given the strong correlation between WSD system accuracy and the reliability of the annotation used for training. We found that sense granularity is a significant factor, but that the number of senses used to label a word is not.
520 $a Finally, we demonstrate that supervised machine learning can be successful with a sense inventory enriched with syntactic and semantic information, such as VerbNet, thereby consolidating the steps needed to create a complex knowledge representation and reasoning system. We trained a classifier to disambiguate a set of verbs with multiple VerbNet class memberships with 90% accuracy, which represents a 61% error reduction over the baseline.
590 $a School code: 0051.
650 4 $a Language, Linguistics. $3 423211
650 4 $a Psychology, Cognitive. $3 423116
690 $a 0290
690 $a 0633
710 2 $a University of Colorado at Boulder. $b Linguistics. $3 423319
773 0 $t Dissertation Abstracts International $g 71-06A.
790 1 0 $a Palmer, Martha, $e advisor
790 1 0 $a Martin, James $e committee member
790 1 0 $a Kim, Albert $e committee member
790 1 0 $a Michaelis-Cummings, Laura $e committee member
790 1 0 $a Erk, Katrin $e committee member
790 $a 0051
791 $a Ph.D.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3403902

筆 0 讀者評論

多媒體

多媒體檔案
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3403902

評論

新增評論分享你的心得

Export

取書館別