國立虎尾科技大學 |

From Event to Story Understanding.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	From Event to Story Understanding./
作者:	Mostafazadeh, Nasrin.
面頁冊數:	1 online resource (149 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-02(E), Section: B.
Contained By:	Dissertation Abstracts International79-02B(E).
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780355241587

From Event to Story Understanding.
Mostafazadeh, Nasrin.

From Event to Story Understanding. - 1 online resource (149 pages)

Source: Dissertation Abstracts International, Volume: 79-02(E), Section: B.

Thesis (Ph.D.)--University of Rochester, 2017.

Includes bibliographical references

Building systems that have natural language understanding capabilities has been one of the oldest and the most challenging pursuits in AI. In this thesis, we present our research on modeling language in terms of `events' and how they interact with each other in time, mainly in the domain of stories.

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

Mode of access: World Wide Web

ISBN: 9780355241587Subjects--Topical Terms:

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

554714
Electronic books.

From Event to Story Understanding.
LDR:03787ntm a2200373Ki 4500 001 916319
005 20181002081323.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355241587
035 $a (MiAaPQ)AAI10618085
035 $a (MiAaPQ)rochester:11510
035 $a AAI10618085
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Mostafazadeh, Nasrin. $3 1190002
245 1 0 $a From Event to Story Understanding.
264 0 $c 2017
300 $a 1 online resource (149 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: 79-02(E), Section: B.
500 $a Adviser: James F. Allen.
502 $a Thesis (Ph.D.)--University of Rochester, 2017.
504 $a Includes bibliographical references
520 $a Building systems that have natural language understanding capabilities has been one of the oldest and the most challenging pursuits in AI. In this thesis, we present our research on modeling language in terms of `events' and how they interact with each other in time, mainly in the domain of stories.
520 $a Deep language understanding, which enables inference and commonsense reasoning, requires systems that have large amounts of knowledge which would enable them to connect surface language to the concepts of the world. A part of our work concerns developing approaches for learning semantically rich knowledge bases on events. First, we present an approach to automatically acquire conceptual knowledge about events in the form of inference rules, which can enable commonsense reasoning. We show that the acquired knowledge is precise and informative which can be employed in different NLP tasks.
520 $a Learning stereotypical structure of related events, in the form of narrative structures or scripts, has been one of the major goals in AI. The research on narrative understanding has been hindered by the lack of a proper evaluation framework. We address this problem by introducing a new framework for evaluating story understanding and script learning: the 'Story Cloze Test (SCT)'. In this test, the system is posed with a short four-sentence narrative context along with two alternative endings to the story, and is tasked with choosing the right ending. Along with the SCT, We have worked on developing the ROCStories corpus of about 100K commonsense short stories, which enables building models for story understanding and story generation. We present various models and baselines for tackling the task of SCT and show that human can perform with an accuracy of 100%.
520 $a One prerequisite for understanding and proper modeling of events and their interactions is to develop a comprehensive semantic framework for representing their variety of relations. We introduce `Causal and Temporal Relation Scheme (CaTeRS)' which is a rich semantic representation for event structures, with an emphasis on the domain of stories. The impact of the SCT and the ROCStories project goes beyond this thesis, where numerous teams and individuals across academia and industry have been using the evaluation framework and the dataset for a variety of purposes. We hope that the methods and the resources presented in this thesis will spur further research on building systems that can effectively model eventful context, understand, and generate logically-sound stories.
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 Rochester. $b Computer Science. $3 1190003
773 0 $t Dissertation Abstracts International $g 79-02B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10618085 $z click for full text (PQDT)