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

A factuality profiler for eventualit...

Brandeis University., Computer Science.

FindBook

Google Book

Amazon

博客來

A factuality profiler for eventualities in text.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	A factuality profiler for eventualities in text./
作者:	Sauri, Roser.
面頁冊數:	317 p.
附註:	Adviser: James Pustejovsky.
Contained By:	Dissertation Abstracts International69-03B.
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3304029
ISBN:	9780549518068

A factuality profiler for eventualities in text.
Sauri, Roser.

A factuality profiler for eventualities in text. - 317 p.

Adviser: James Pustejovsky.

Thesis (Ph.D.)--Brandeis University, 2008.

My dissertation aims at designing and developing a factuality profiler, namely a tool devoted to the identification of the factuality degree associated to eventualities mentioned in discourse.

ISBN: 9780549518068Subjects--Topical Terms:

626642
Computer Science.

A factuality profiler for eventualities in text.
LDR:03516nmm 2200397 a 45 001 862805
005 20100721
008 100721s2008 ||||||||||||||||| ||eng d
020 $a 9780549518068
035 $a (UMI)AAI3304029
035 $a AAI3304029
040 $a UMI $c UMI
100 1 $a Sauri, Roser. $3 1030662
245 1 2 $a A factuality profiler for eventualities in text.
300 $a 317 p.
500 $a Adviser: James Pustejovsky.
500 $a Source: Dissertation Abstracts International, Volume: 69-03, Section: B, page: 1748.
502 $a Thesis (Ph.D.)--Brandeis University, 2008.
520 $a My dissertation aims at designing and developing a factuality profiler, namely a tool devoted to the identification of the factuality degree associated to eventualities mentioned in discourse.
520 $a Event factuality is the level of information expressing the factual status of eventualities mentioned in text. That is, it conveys whether eventualities are characterized as corresponding to facts, to possibilities, or to situations that do not hold in the world. As such, it touches on two categories more standardly assumed in the literature: modality and evidentiality. They both have been widely discussed in linguistics and philosophy, but it is not until recently that have started to receive some attention within the area of NLP.
520 $a Factuality is a necessary component for reasoning about eventualities in discourse. Inferences derived from events that have not happened, or that are possible, are different from those derived from events judged as factual. It is also essential for any task involving temporal ordering. The creation of event timelines needs to be aware of the different status of eventualities presented as uncertain or counterfactual.
520 $a Event factuality cannot be conceived independently from language users, who are understood here as the sources of factuality information. Their inclusion in the model is fundamental. Two sources can assign different factuality values to the same event. Because of that, the factuality profiler must be capable of representing different and possibly contradictory information about the factuality nature of any event.
520 $a De Facto, the tool I am presenting here, is grounded on the linguistic strategies we speakers employ to signal degrees of factuality in discourse. These involve information at different levels: lexical, syntactic, and rhetoric. De Facto implements an algorithm based on the grammatical structuring of factuality in languages like English, and is informed with a set of linguistic resources compiled from a data-driven approach.
520 $a For evaluating De Facto, I created FactBank, a corpus annotated with factuality information. The interannotation agreement score for the task of assigning factuality values to events is kcohen = 0.81. Running De Facto against the gold standard results in F1=0.74 (macro-averaging), F1=0.85 (micro-averaging) and, in terms of interannotation agreement, kcohen =0.72.
590 $a School code: 0021.
650 4 $a Computer Science. $3 626642
650 4 $a Language, General. $3 1018089
650 4 $a Language, Linguistics. $3 1018079
690 $a 0290
690 $a 0679
690 $a 0984
710 2 $a Brandeis University. $b Computer Science. $3 1030661
773 0 $t Dissertation Abstracts International $g 69-03B.
790 $a 0021
790 1 0 $a Alterman, Richard $e committee member
790 1 0 $a Badia, Toni $e committee member
790 1 0 $a Karttunen, Lauri $e committee member
790 1 0 $a Pustejovsky, James, $e advisor
790 1 0 $a Verhagen, Marc $e committee member
791 $a Ph.D.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3304029