東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Understanding, Building, and Evaluat...

Chan, David M.,

Linked to FindBook

Google Book

Amazon

博客來

Understanding, Building, and Evaluating Models for Context Aware Conditional Natural Language Generation /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Understanding, Building, and Evaluating Models for Context Aware Conditional Natural Language Generation // David M Chan.
Author:	Chan, David M.,
Description:	1 electronic resource (252 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
Contained By:	Dissertations Abstracts International86-03B.
Subject:	Speech therapy. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31235505
ISBN:	9798384447702

Understanding, Building, and Evaluating Models for Context Aware Conditional Natural Language Generation /
Chan, David M.,

Understanding, Building, and Evaluating Models for Context Aware Conditional Natural Language Generation /David M Chan. - 1 electronic resource (252 pages)

Source: Dissertations Abstracts International, Volume: 86-03, Section: B.

If you ask a human to describe an image, they might do so in a thousand different ways. Each of these descriptions depends not only on the image but also on a rich tapestry of contextual hints and clues surrounding the image (up to and including the person doing the describing themselves). Until now, the field of conditional natural language generation has focused almost solely on the perception component of the task: how do we perceive what is in the stimulus -- be it audio, visual, or textual -- and relay it to the user? In this dissertation, we argue that models that focus solely on the stimulus (and not the associated context) suffer significant shortcomings in their ability to generate language that aligns well with human judgments of quality and content while decreasing their overall utility for downstream tasks. This dissertation focuses on three core objectives in the pursuit of building a context-aware conditional natural language generation (CNLG) model: (1) capturing and understanding the information within, among, and between generated conditional texts, (2) developing multimodal models that better integrate contextual information, and (3) designing CNLG evaluation methodologies that better align with human judgment. Through these objectives, we demonstrate the power of context in natural language generation and help to answer the question: "How can we understand, build, and evaluate context-aware models for conditional natural language generation?".

English

ISBN: 9798384447702Subjects--Topical Terms:

520446
Speech therapy.
Subjects--Index Terms:

Automatic speech recognition

Understanding, Building, and Evaluating Models for Context Aware Conditional Natural Language Generation /
LDR:02947nmm a22004213i 4500 001 2431573
005 20250616055530.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798384447702
035 $a (MiAaPQD)AAI31235505
035 $a AAI31235505
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Chan, David M., $e author. $3 3820451
245 1 0 $a Understanding, Building, and Evaluating Models for Context Aware Conditional Natural Language Generation / $c David M Chan.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (252 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: Dissertations Abstracts International, Volume: 86-03, Section: B.
500 $a Advisors: Canny, John Committee members: Darrell, Trevor; Gopnik, Alison.
502 $b Ph.D. $c University of California, Berkeley $d 2024.
520 $a If you ask a human to describe an image, they might do so in a thousand different ways. Each of these descriptions depends not only on the image but also on a rich tapestry of contextual hints and clues surrounding the image (up to and including the person doing the describing themselves). Until now, the field of conditional natural language generation has focused almost solely on the perception component of the task: how do we perceive what is in the stimulus -- be it audio, visual, or textual -- and relay it to the user? In this dissertation, we argue that models that focus solely on the stimulus (and not the associated context) suffer significant shortcomings in their ability to generate language that aligns well with human judgments of quality and content while decreasing their overall utility for downstream tasks. This dissertation focuses on three core objectives in the pursuit of building a context-aware conditional natural language generation (CNLG) model: (1) capturing and understanding the information within, among, and between generated conditional texts, (2) developing multimodal models that better integrate contextual information, and (3) designing CNLG evaluation methodologies that better align with human judgment. Through these objectives, we demonstrate the power of context in natural language generation and help to answer the question: "How can we understand, build, and evaluate context-aware models for conditional natural language generation?".
546 $a English
590 $a School code: 0028
650 4 $a Speech therapy. $3 520446
650 4 $a Computer science. $3 523869
653 $a Automatic speech recognition
653 $a Context-aware generation
653 $a Large language models
653 $a Natural language processing
690 $a 0800
690 $a 0984
690 $a 0460
710 2 $a University of California, Berkeley. $b Electrical Engineering & Computer Sciences. $e degree granting institution. $3 3819104
720 1 $a Canny, John $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-03B.
790 $a 0028
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31235505