본문

서브메뉴

Unsupervised Text Generation and Its Application to News Interfaces- [electronic resource]
Unsupervised Text Generation and Its Application to News Interfaces - [electronic resource...
Unsupervised Text Generation and Its Application to News Interfaces- [electronic resource]

상세정보

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  
Human computer interaction
키워드  
Natural language processing
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.

MARC

 008240612s2021      us  |||||||||||||||c||eng  d
■001000016931038
■00520240214095858
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380618724
■035    ▼a(MiAaPQ)AAI28767878
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aLaban,  Philippe.
■24510▼aUnsupervised  Text  Generation  and  Its  Application  to  News  Interfaces▼h[electronic  resource]
■260    ▼a[S.l.]:▼bUniversity  of  California,  Berkeley.  ▼c2021
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2021
■300    ▼a1  online  resource(159  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-04,  Section:  A.
■500    ▼aAdvisor:  Hearst,  Marti  A.;Canny,  John.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2021.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aRecent  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.
■590    ▼aSchool  code:  0028.
■650  4▼aComputer  science.
■650  4▼aMass  communications.
■650  4▼aComputer  engineering.
■653    ▼aHuman  computer  interaction
■653    ▼aNatural  language  processing
■653    ▼aNews  interfaces
■653    ▼aSimplification
■653    ▼aSummarization
■690    ▼a0800
■690    ▼a0984
■690    ▼a0464
■690    ▼a0708
■71020▼aUniversity  of  California,  Berkeley▼bElectrical  Engineering  &  Computer  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g85-04A.
■773    ▼tDissertation  Abstract  International
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2021
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16931038▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF08449 전자도서 마이폴더 부재도서신고 비도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.