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

FindBook

Google Book

Amazon

博客來

Automated Generation and Detection of Novel On-Topic Metaphors Using Machine Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Automated Generation and Detection of Novel On-Topic Metaphors Using Machine Learning./
作者:	Brooks, Jennifer Trull.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	157 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-10, Section: B.
Contained By:	Dissertations Abstracts International83-10B.
標題:	Artificial intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29064794
ISBN:	9798209990116

Automated Generation and Detection of Novel On-Topic Metaphors Using Machine Learning.
Brooks, Jennifer Trull.

Automated Generation and Detection of Novel On-Topic Metaphors Using Machine Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 157 p.

Source: Dissertations Abstracts International, Volume: 83-10, Section: B.

Thesis (Ph.D.)--The George Washington University, 2022.

This item must not be sold to any third party vendors.

The primary goal of this research is to automatically generate novel metaphors, where a generated metaphor can be interpreted by humans and based on a topic provided as input to the generator. This research is motivated by the idea that metaphors can inspire people with fresh, creative thoughts, and foster greater trust between humans and machines by making the machines more creative and human-like in their use of language.Metaphor generation requires metaphor detection to ensure that a metaphor was generated. On-topic metaphor generation requires identifying the topic in the generated metaphor and then measuring the similarity of the identified topic to the intended topic, or measuring the relatedness of the generated text to the topic. Novel metaphor generation requires tests of originality and style-adherence. This research also introduces metrics for novelty and originality, where no standards currently exist. Our approach to metaphor generation can be organized into two primary parts. First, train a language model on the language of metaphors. Second, build quality assurance mechanisms to automatically encourage style-adherence, fluency, originality, and topic-relatedness in the outputs. We emulate the processes that humans go through when they are trying to think of a metaphor to include in their creative writing. We may generate many candidates that fail our quality assurance tests before generating one that we would put in writing. To assess the subjective quality of our generated metaphors, we conducted two experiments with human participants. We found that our trained models performed better than random on the task of generating a metaphor on-topic, and there was a positive correlation (0.625) between whether the topic was identifiable and a participant thought that the metaphor was written by a human. Furthermore, we found that the participants, on average, thought that 60% of the randomly selected metaphor generations were written by a human and inspiring and rich in meaning.

ISBN: 9798209990116Subjects--Topical Terms:

516317
Artificial intelligence.
Subjects--Index Terms:

Figurative language

Automated Generation and Detection of Novel On-Topic Metaphors Using Machine Learning.
LDR:03265nmm a2200385 4500 001 2352204
005 20221118093841.5
008 241004s2022 ||||||||||||||||| ||eng d
020 $a 9798209990116
035 $a (MiAaPQ)AAI29064794
035 $a AAI29064794
040 $a MiAaPQ $c MiAaPQ
100 1 $a Brooks, Jennifer Trull. $0 (orcid)0000-0002-1768-4926 $3 3691824
245 1 0 $a Automated Generation and Detection of Novel On-Topic Metaphors Using Machine Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 157 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-10, Section: B.
500 $a Advisor: Youssef, Abdou.
502 $a Thesis (Ph.D.)--The George Washington University, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a The primary goal of this research is to automatically generate novel metaphors, where a generated metaphor can be interpreted by humans and based on a topic provided as input to the generator. This research is motivated by the idea that metaphors can inspire people with fresh, creative thoughts, and foster greater trust between humans and machines by making the machines more creative and human-like in their use of language.Metaphor generation requires metaphor detection to ensure that a metaphor was generated. On-topic metaphor generation requires identifying the topic in the generated metaphor and then measuring the similarity of the identified topic to the intended topic, or measuring the relatedness of the generated text to the topic. Novel metaphor generation requires tests of originality and style-adherence. This research also introduces metrics for novelty and originality, where no standards currently exist. Our approach to metaphor generation can be organized into two primary parts. First, train a language model on the language of metaphors. Second, build quality assurance mechanisms to automatically encourage style-adherence, fluency, originality, and topic-relatedness in the outputs. We emulate the processes that humans go through when they are trying to think of a metaphor to include in their creative writing. We may generate many candidates that fail our quality assurance tests before generating one that we would put in writing. To assess the subjective quality of our generated metaphors, we conducted two experiments with human participants. We found that our trained models performed better than random on the task of generating a metaphor on-topic, and there was a positive correlation (0.625) between whether the topic was identifiable and a participant thought that the metaphor was written by a human. Furthermore, we found that the participants, on average, thought that 60% of the randomly selected metaphor generations were written by a human and inspiring and rich in meaning.
590 $a School code: 0075.
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
650 4 $a Language arts. $3 532624
653 $a Figurative language
653 $a Machine learning
653 $a Metaphor
653 $a Natural language generation (NLG)
653 $a Natural language processing (NLP)
653 $a Topic Inference
690 $a 0800
690 $a 0984
690 $a 0279
710 2 $a The George Washington University. $b Computer Science. $3 1026593
773 0 $t Dissertations Abstracts International $g 83-10B.
790 $a 0075
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29064794