본문

Building Blocks for Data-Driven Theories of Language Understanding- [electronic resource]
Building Blocks for Data-Driven Theories of Language Understanding - [electronic resource]
ข้อมูลเนื้อหา
Building Blocks for Data-Driven Theories of Language Understanding- [electronic resource]
자료유형  
 학위논문파일 국외
최종처리일시  
20240214101235
ISBN  
9798379912116
DDC  
401
저자명  
Michael, Julian.
서명/저자  
Building Blocks for Data-Driven Theories of Language Understanding - [electronic resource]
발행사항  
[S.l.]: : University of Washington., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(163 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 85-01, Section: B.
주기사항  
Advisor: Zettlemoyer, Luke.
학위논문주기  
Thesis (Ph.D.)--University of Washington, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약I propose a paradigm for scientific progress in natural language processing, centered around the development of data-driven theories of language understanding. The central idea is to collect data in tightly scoped, carefully defined ways which allow for exhaustive annotation of a behavioral phenomenon of interest. With such data, we can use machine learning to construct explanatory theories of these phenomena which can be used as building blocks for intelligible AI systems. After laying some conceptual groundwork for the idea, I describe a series of investigations into the development of data and theory for representations of shallow semantic structure in natural language - in particular, using Question-Answer driven Semantic Role Labeling (QA-SRL), a simple schema for annotating verbal predicate-argument structure using highly constrained question-answer pairs. While this just scratches the surface of the complex language behaviors of interest in AI, I outline principles for data collection and theoretical modeling which can inform future scientific progress.
일반주제명  
Linguistics.
일반주제명  
Computer science.
키워드  
Crowdsourcing
키워드  
Pragmatism
키워드  
Semantic roles
키워드  
Natural language processing
키워드  
Scientific progress
기타저자  
University of Washington Computer Science and Engineering
기본자료저록  
Dissertations Abstracts International. 85-01B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.
New Books MORE
최근 3년간 통계입니다.

ค้นหาข้อมูลรายละเอียด

  • จองห้องพัก
  • ไม่อยู่
  • โฟลเดอร์ของฉัน
  • ขอดูแรก
  • 비도서대출신청
  • 야간 도서대출신청
วัสดุ
Reg No. Call No. ตำแหน่งที่ตั้ง สถานะ ยืมข้อมูล
TF09083 전자도서
마이폴더 부재도서신고 비도서대출신청

* จองมีอยู่ในหนังสือยืม เพื่อให้การสำรองที่นั่งคลิกที่ปุ่มจองห้องพัก

해당 도서를 다른 이용자가 함께 대출한 도서

Related Popular Books

로그인 후 이용 가능합니다.