東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Rich Linguistic Structure from Large...

Yamangil, Elif.

FindBook

Google Book

Amazon

博客來

Rich Linguistic Structure from Large-Scale Web Data.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Rich Linguistic Structure from Large-Scale Web Data./
作者:	Yamangil, Elif.
面頁冊數:	169 p.
附註:	Source: Dissertation Abstracts International, Volume: 75-02(E), Section: B.
Contained By:	Dissertation Abstracts International75-02B(E).
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3600271
ISBN:	9781303503375

Rich Linguistic Structure from Large-Scale Web Data.
Yamangil, Elif.

Rich Linguistic Structure from Large-Scale Web Data. - 169 p.

Source: Dissertation Abstracts International, Volume: 75-02(E), Section: B.

Thesis (Ph.D.)--Harvard University, 2013.

The past two decades have shown an unexpected effectiveness of Web-scale data in natural language processing. Even the simplest models, when paired with unprecedented amounts of unstructured and unlabeled Web data, have been shown to outperform sophisticated ones. It has been argued that the effectiveness of Web-scale data has undermined the necessity of sophisticated modeling or laborious data set curation. In this thesis, we argue for and illustrate an alternative view, that Web-scale data not only serves to improve the performance of simple models, but also can allow the use of qualitatively more sophisticated models that would not be deployable otherwise, leading to even further performance gains.

ISBN: 9781303503375Subjects--Topical Terms:

626642
Computer Science.

Rich Linguistic Structure from Large-Scale Web Data.
LDR:03034nam a2200325 4500 001 1958977
005 20140512081900.5
008 150210s2013 ||||||||||||||||| ||eng d
020 $a 9781303503375
035 $a (MiAaPQ)AAI3600271
035 $a AAI3600271
040 $a MiAaPQ $c MiAaPQ
100 1 $a Yamangil, Elif. $3 2094239
245 1 0 $a Rich Linguistic Structure from Large-Scale Web Data.
300 $a 169 p.
500 $a Source: Dissertation Abstracts International, Volume: 75-02(E), Section: B.
500 $a Adviser: Stuart M. Shieber.
502 $a Thesis (Ph.D.)--Harvard University, 2013.
520 $a The past two decades have shown an unexpected effectiveness of Web-scale data in natural language processing. Even the simplest models, when paired with unprecedented amounts of unstructured and unlabeled Web data, have been shown to outperform sophisticated ones. It has been argued that the effectiveness of Web-scale data has undermined the necessity of sophisticated modeling or laborious data set curation. In this thesis, we argue for and illustrate an alternative view, that Web-scale data not only serves to improve the performance of simple models, but also can allow the use of qualitatively more sophisticated models that would not be deployable otherwise, leading to even further performance gains.
520 $a We investigate this hypothesis through the use of both parametric and Bayesian non-parametric modeling techniques. First, by comparing rich parametric models against simpler models, we show that richer modeling of Web data brings about qualitative and quantitative performance gains. Experimental results in the application domain of sentence compression show that richer models lead to systems with improved robustness and generalization power. In the domain of lexical correction we augment a coarse generative model with a discriminative reranking component that incorporates richer contextual information and achieve improvements in performance.
520 $a Second, by using the Bayesian nonparametric modeling framework, we show how to induce rich models in fully automatic, data-driven ways as opposed to heuristically. We propose principled and unified solutions to not only the estimation but also the model selection problem of the linguistically sophisticated grammar formalisms of tree-insertion grammars and tree-adjoining grammars. When evaluated in the domain of syntactic parsing, our induced grammars do not only lead to improved performance but are also compact, allowing for efficient computational processing and linguistic analysis. Further we show that these compact grammars can achieve the same performance gains as the parametric rich models in Web-scale sentence compression experiments.
590 $a School code: 0084.
650 4 $a Computer Science. $3 626642
650 4 $a Language, Linguistics. $3 1018079
650 4 $a Statistics. $3 517247
650 4 $a Web Studies. $3 1026830
690 $a 0984
690 $a 0290
690 $a 0463
690 $a 0646
710 2 $a Harvard University. $b Engineering and Applied Sciences. $3 2093136
773 0 $t Dissertation Abstracts International $g 75-02B(E).
790 $a 0084
791 $a Ph.D.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3600271