國立虎尾科技大學 |

Improving Reliability in Dialogue Systems.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Improving Reliability in Dialogue Systems./
作者:	Gupta, Prakhar.
面頁冊數:	1 online resource (196 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-02, Section: B.
Contained By:	Dissertations Abstracts International85-02B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798380144582

Improving Reliability in Dialogue Systems.
Gupta, Prakhar.

Improving Reliability in Dialogue Systems. - 1 online resource (196 pages)

Source: Dissertations Abstracts International, Volume: 85-02, Section: B.

Thesis (Ph.D.)--Carnegie Mellon University, 2023.

Includes bibliographical references

Dialogue systems have undergone significant advancements by leveraging large public corpora and advancements in neural architectures. Thanks to large pre-trained language models and recent developments in neural networks, dialogue generation systems are now capable of producing fluent and engaging responses across various dialogue contexts. However, black-box nature and heightened complexity of end-to-end neural dialogue models make them susceptible to unknown failure modes that often emerge only after deployment. To improve the reliability of neural dialogue models for practical applications, several challenges need to be addressed. Firstly, creating robust and bias-free evaluation and ranking models for dialogue is a not straight-forward as it requires careful consideration of various factors such as context, coherence, relevance, and user satisfaction. Secondly, controlling the outputs of dialogue response generation models to align with developers' intended goals presents a challenge. Current approaches often lack the necessary flexibility, intuitiveness, interpretability, and data-efficiency to enable fine-grained control over the generated responses. Lastly, enhancing safety measures is crucial to ensure that dialogue systems do not generate offensive or factually incorrect responses, thereby avoiding unintended harm to users.This thesis addresses the challenges in enhancing the reliability of neural dialogue models by introducing novel techniques for robust evaluation and providing finer, more intuitive control over the response generation process. The thesis comprises two main parts that tackle these challenges. The first part focuses on the development of techniques for creating robust dialogue response evaluation and ranking algorithms. These techniques utilize multiple references, automatically generated adversarial responses, and improved benchmarking methods for assessing factuality. By incorporating these approaches, the thesis aims to establish more reliable and comprehensive evaluation metrics for dialogue systems, ensuring a more accurate assessment of their performance. The second part of the thesis proposes techniques to empower developers with flexible, intuitive, and interpretable means of controlling the generation process. This includes the utilization of templates, examples, instructions, and guidelines to guide the system towards generating responses that align with specific tasks and developer intent. Additionally, this part introduces safety mechanisms designed to prevent misuse and harm to users. These safety mechanisms utilize natural language instructions and guidelines to ensure responsible and ethical behavior of the dialogue systems.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380144582Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

ChatbotsIndex Terms--Genre/Form:

554714
Electronic books.

Improving Reliability in Dialogue Systems.
LDR:04043ntm a22003857 4500 001 1146400
005 20240812064606.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380144582
035 $a (MiAaPQ)AAI30571710
035 $a AAI30571710
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Gupta, Prakhar. $3 1471785
245 1 0 $a Improving Reliability in Dialogue Systems.
264 0 $c 2023
300 $a 1 online resource (196 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: 85-02, Section: B.
500 $a Advisor: Bigham, Jeffrey P.
502 $a Thesis (Ph.D.)--Carnegie Mellon University, 2023.
504 $a Includes bibliographical references
520 $a Dialogue systems have undergone significant advancements by leveraging large public corpora and advancements in neural architectures. Thanks to large pre-trained language models and recent developments in neural networks, dialogue generation systems are now capable of producing fluent and engaging responses across various dialogue contexts. However, black-box nature and heightened complexity of end-to-end neural dialogue models make them susceptible to unknown failure modes that often emerge only after deployment. To improve the reliability of neural dialogue models for practical applications, several challenges need to be addressed. Firstly, creating robust and bias-free evaluation and ranking models for dialogue is a not straight-forward as it requires careful consideration of various factors such as context, coherence, relevance, and user satisfaction. Secondly, controlling the outputs of dialogue response generation models to align with developers' intended goals presents a challenge. Current approaches often lack the necessary flexibility, intuitiveness, interpretability, and data-efficiency to enable fine-grained control over the generated responses. Lastly, enhancing safety measures is crucial to ensure that dialogue systems do not generate offensive or factually incorrect responses, thereby avoiding unintended harm to users.This thesis addresses the challenges in enhancing the reliability of neural dialogue models by introducing novel techniques for robust evaluation and providing finer, more intuitive control over the response generation process. The thesis comprises two main parts that tackle these challenges. The first part focuses on the development of techniques for creating robust dialogue response evaluation and ranking algorithms. These techniques utilize multiple references, automatically generated adversarial responses, and improved benchmarking methods for assessing factuality. By incorporating these approaches, the thesis aims to establish more reliable and comprehensive evaluation metrics for dialogue systems, ensuring a more accurate assessment of their performance. The second part of the thesis proposes techniques to empower developers with flexible, intuitive, and interpretable means of controlling the generation process. This includes the utilization of templates, examples, instructions, and guidelines to guide the system towards generating responses that align with specific tasks and developer intent. Additionally, this part introduces safety mechanisms designed to prevent misuse and harm to users. These safety mechanisms utilize natural language instructions and guidelines to ensure responsible and ethical behavior of the dialogue systems.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
653 $a Chatbots
653 $a Conversational agents
653 $a Dialogue systems
653 $a Ranking algorithms
653 $a Neural architectures
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Carnegie Mellon University. $b Language Technologies Institute. $3 1471771
773 0 $t Dissertations Abstracts International $g 85-02B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30571710 $z click for full text (PQDT)