國立虎尾科技大學 |

On-the-Job Continual and Interactive Learning of Factual Knowledge and Language Grounding.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	On-the-Job Continual and Interactive Learning of Factual Knowledge and Language Grounding./
作者:	Mazumder, Sahisnu.
面頁冊數:	1 online resource (189 pages)
附註:	Source: Dissertations Abstracts International, Volume: 83-09, Section: B.
Contained By:	Dissertations Abstracts International83-09B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798790640452

On-the-Job Continual and Interactive Learning of Factual Knowledge and Language Grounding.
Mazumder, Sahisnu.

On-the-Job Continual and Interactive Learning of Factual Knowledge and Language Grounding. - 1 online resource (189 pages)

Source: Dissertations Abstracts International, Volume: 83-09, Section: B.

Thesis (Ph.D.)--University of Illinois at Chicago, 2021.

Includes bibliographical references

Dialogue systems, commonly called as Chatbots, have gained escalating popularity in recent times due to their wide-spread applications in carrying out chit-chat conversations with users and accomplishing tasks as personal assistants. These systems are typically trained from manually-labeled data and/or written with handcrafted rules and often, use explicit knowledge bases (KBs) (compiled by human experts) to help generate quality responses and support information-seeking conversations. However, as the complied data and handcrafted rules are always limited by human efforts, it cannot cover all possible variations of natural language. Also, as the KBs are inherently incomplete and remain fixed during conversation, it limits the systems' ability to answer questions from users and ground knowledge in conversation modeling. Thus, when the systems are deployed, the level of user satisfaction is often low. In this thesis, we propose methods to give the chatbots the ability to continuously and interactively learn (1) new world knowledge and (2) new language expressions to ground them to actions, during conversation, i.e. "on-the-job" by themselves so that as the systems chat more and more with users, they become more and more knowledgeable and improve their performance over time. To formalize the idea of "On-the-job Continual and Interactive Learning", we propose a novel paradigm called Lifelong INteractive Learning in Conversation (LINC) and design frameworks for factual knowledge learning and language learning in dialogues. We leverage the opportunity- when a user asks the dialogue system a question which the system is unable to answer (due to the lack of knowledge in its current KB) as the scope for learning new factual knowledge and propose two frameworks, viz. Continuous and Interactive Learning of Knowledge (CILK) and Interactive Knowledge Acquisition and Inference (IKAI) to enable interactive factual knowledge learning in dialogues. We also propose a novel framework called Command Matching and Learning (CML) to automatically build self-adaptive NLIs for any API-driven application. CML continually learns new language expressions in multi-turn dialogues with end users after model deployment and improves its natural language understanding and grounding abilities over time. We build Simulated Users (from the publicly available standard datasets) to interact with the systems (i.e. answering the questions asked by the systems) and use them for online evaluation. Our experimental evaluation and analysis show that with more knowledge accumulated over time, the systems are able to learn better, answering more factual questions from users and improving grounding of natural language commands.

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

Mode of access: World Wide Web

ISBN: 9798790640452Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Dialogue and Interactive SystemsIndex Terms--Genre/Form:

554714
Electronic books.

On-the-Job Continual and Interactive Learning of Factual Knowledge and Language Grounding.
LDR:04330ntm a22004577 4500 001 1147211
005 20240909100726.5
006 m o d
007 cr bn ---uuuuu
008 250605s2021 xx obm 000 0 eng d
020 $a 9798790640452
035 $a (MiAaPQ)AAI29077201
035 $a (MiAaPQ)0799vireo2927Mazumder
035 $a AAI29077201
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Mazumder, Sahisnu. $3 1472878
245 1 0 $a On-the-Job Continual and Interactive Learning of Factual Knowledge and Language Grounding.
264 0 $c 2021
300 $a 1 online resource (189 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: 83-09, Section: B.
500 $a Advisor: Liu, Bing.
502 $a Thesis (Ph.D.)--University of Illinois at Chicago, 2021.
504 $a Includes bibliographical references
520 $a Dialogue systems, commonly called as Chatbots, have gained escalating popularity in recent times due to their wide-spread applications in carrying out chit-chat conversations with users and accomplishing tasks as personal assistants. These systems are typically trained from manually-labeled data and/or written with handcrafted rules and often, use explicit knowledge bases (KBs) (compiled by human experts) to help generate quality responses and support information-seeking conversations. However, as the complied data and handcrafted rules are always limited by human efforts, it cannot cover all possible variations of natural language. Also, as the KBs are inherently incomplete and remain fixed during conversation, it limits the systems' ability to answer questions from users and ground knowledge in conversation modeling. Thus, when the systems are deployed, the level of user satisfaction is often low. In this thesis, we propose methods to give the chatbots the ability to continuously and interactively learn (1) new world knowledge and (2) new language expressions to ground them to actions, during conversation, i.e. "on-the-job" by themselves so that as the systems chat more and more with users, they become more and more knowledgeable and improve their performance over time. To formalize the idea of "On-the-job Continual and Interactive Learning", we propose a novel paradigm called Lifelong INteractive Learning in Conversation (LINC) and design frameworks for factual knowledge learning and language learning in dialogues. We leverage the opportunity- when a user asks the dialogue system a question which the system is unable to answer (due to the lack of knowledge in its current KB) as the scope for learning new factual knowledge and propose two frameworks, viz. Continuous and Interactive Learning of Knowledge (CILK) and Interactive Knowledge Acquisition and Inference (IKAI) to enable interactive factual knowledge learning in dialogues. We also propose a novel framework called Command Matching and Learning (CML) to automatically build self-adaptive NLIs for any API-driven application. CML continually learns new language expressions in multi-turn dialogues with end users after model deployment and improves its natural language understanding and grounding abilities over time. We build Simulated Users (from the publicly available standard datasets) to interact with the systems (i.e. answering the questions asked by the systems) and use them for online evaluation. Our experimental evaluation and analysis show that with more knowledge accumulated over time, the systems are able to learn better, answering more factual questions from users and improving grounding of natural language commands.
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
650 4 $a Computer engineering. $3 569006
650 4 $a Information technology. $3 559429
650 4 $a Artificial intelligence. $3 559380
650 4 $a Information science. $3 561178
653 $a Dialogue and Interactive Systems
653 $a Chatbots
653 $a Lifelong Interactive Learning
653 $a Continual Learning
653 $a On the job Learning
653 $a Learning during Conversation
653 $a Learning after Model Deployment
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0489
690 $a 0464
690 $a 0723
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Illinois at Chicago. $b Computer Science. $3 1467155
773 0 $t Dissertations Abstracts International $g 83-09B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29077201 $z click for full text (PQDT)