東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Data-driven approaches for paraphras...

Xu, Wei.

Linked to FindBook

Google Book

Amazon

博客來

Data-driven approaches for paraphrasing across language variations.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Data-driven approaches for paraphrasing across language variations./
Author:	Xu, Wei.
Description:	111 p.
Notes:	Source: Dissertation Abstracts International, Volume: 75-07(E), Section: B.
Contained By:	Dissertation Abstracts International75-07B(E).
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3614914
ISBN:	9781303806117

Data-driven approaches for paraphrasing across language variations.
Xu, Wei.

Data-driven approaches for paraphrasing across language variations. - 111 p.

Source: Dissertation Abstracts International, Volume: 75-07(E), Section: B.

Thesis (Ph.D.)--New York University, 2014.

Our language changes very rapidly, accompanying political, social and cultural trends, as well as the evolution of science and technology. The Internet, especially the social media, has accelerated this process of change. This poses a severe challenge for both human beings and natural language processing (NLP) systems, which usually only model a snapshot of language presented in the form of text corpora within a certain domain and time frame.

ISBN: 9781303806117Subjects--Topical Terms:

626642
Computer Science.

Data-driven approaches for paraphrasing across language variations.
LDR:02329nam a2200301 4500 001 1962434
005 20140805141059.5
008 150210s2014 ||||||||||||||||| ||eng d
020 $a 9781303806117
035 $a (MiAaPQ)AAI3614914
035 $a AAI3614914
040 $a MiAaPQ $c MiAaPQ
100 1 $a Xu, Wei. $3 923895
245 1 0 $a Data-driven approaches for paraphrasing across language variations.
300 $a 111 p.
500 $a Source: Dissertation Abstracts International, Volume: 75-07(E), Section: B.
500 $a Adviser: Ralph Grishman.
502 $a Thesis (Ph.D.)--New York University, 2014.
520 $a Our language changes very rapidly, accompanying political, social and cultural trends, as well as the evolution of science and technology. The Internet, especially the social media, has accelerated this process of change. This poses a severe challenge for both human beings and natural language processing (NLP) systems, which usually only model a snapshot of language presented in the form of text corpora within a certain domain and time frame.
520 $a While much previous effort has investigated monolingual paraphrase and bilingual translation, we focus on modeling meaning-preserving transformations between variants of a single language. We use Shakespearean and Internet language as examples to investigate various aspects of this new paraphrase problem, including acquisition, generation, detection and evaluation.
520 $a A data-driven methodology is applied intensively throughout the course of this study. Several paraphrase corpora are constructed using automatic techniques, experts and crowdsourcing platforms. Paraphrase systems are trained and evaluated by using these data as a cornerstone. We show that even with a very noisy or a relatively small amount of parallel training data, it is possible to learn paraphrase models which capture linguistic phenomena. This work expands the scope of paraphrase studies to targeting different language variations, and more potential applications, such as text normalization and domain adaptation.
590 $a School code: 0146.
650 4 $a Computer Science. $3 626642
650 4 $a Language, Linguistics. $3 1018079
690 $a 0984
690 $a 0290
710 2 $a New York University. $b Computer Science. $3 1065424
773 0 $t Dissertation Abstracts International $g 75-07B(E).
790 $a 0146
791 $a Ph.D.
792 $a 2014
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3614914