Unsupervised Text Generation and Its Application to News Interfaces- [electronic resource]
Unsupervised Text Generation and Its Application to News Interfaces- [electronic resource]
- 자료유형
- 학위논문파일 국외
- 최종처리일시
- 20240214095858
- ISBN
- 9798380618724
- DDC
- 004
- 저자명
- Laban, Philippe.
- 서명/저자
- Unsupervised Text Generation and Its Application to News Interfaces - [electronic resource]
- 발행사항
- [S.l.]: : University of California, Berkeley., 2021
- 발행사항
- Ann Arbor : : ProQuest Dissertations & Theses,, 2021
- 형태사항
- 1 online resource(159 p.)
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-04, Section: A.
- 주기사항
- Advisor: Hearst, Marti A.;Canny, John.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Berkeley, 2021.
- 사용제한주기
- This item must not be sold to any third party vendors.
- 초록/해제
- 요약Recent progress in automated text generation relies predominantly on the use of large datasets, sometimes requiring millions of examples for each application setting. In the first part of this thesis, we advance the field by developing novel text generation methods that balance the goals of fluency, consistency, and relevancy without requiring any training data. We achieve this objective on tasks such as text summarization and simplification by directly defining a multi-component reward, and training text generators to optimize this objective. The novel approaches that we introduce perform better than all existing unsupervised approaches and in many cases outperform those that rely on large datasets.The second part of the thesis incorporates text generation into interfaces to help news readers navigate complex, unfolding news topics. We build a novel representation of news stories at scale and integrate new summarization, question generation and question answering modules into a chatbot and an automated interactive podcast. Human evaluations confirm that even though imperfect systems introduce friction for the user, they can serve as powerful tools to stimulate reader curiosity and help readers dive deeper into unfolding topics.
- 일반주제명
- Computer science.
- 일반주제명
- Mass communications.
- 일반주제명
- Computer engineering.
- 키워드
- News interfaces
- 키워드
- Simplification
- 키워드
- Summarization
- 기타저자
- University of California, Berkeley Electrical Engineering & Computer Sciences
- 기본자료저록
- Dissertations Abstracts International. 85-04A.
- 기본자료저록
- Dissertation Abstract International
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.