Classification-and-Ranking Architecture Based on Intentions for Response Generation Systems

Existing response generation accounts only concern with generation of words into sentences, either by means of grammar or statistical distribution. While the resulting utterance may be inarguably sophisticated, the impact may be not as forceful. We believe that the design for response generation...

Full description

Saved in:

Bibliographic Details
Main Author:	Mustapha, Aida
Format:	Thesis
Language:	English
Published:	2008
Subjects:	Conditioned response
Online Access:	http://psasir.upm.edu.my/id/eprint/5894/1/FSKTM_2008_1%20IR.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-upm-ir.5894
record_format	uketd_dc
spelling	my-upm-ir.58942022-01-25T04:29:39Z Classification-and-Ranking Architecture Based on Intentions for Response Generation Systems 2008-03 Mustapha, Aida Existing response generation accounts only concern with generation of words into sentences, either by means of grammar or statistical distribution. While the resulting utterance may be inarguably sophisticated, the impact may be not as forceful. We believe that the design for response generation requires more than grammar rules or some statistical distributions, but more intuitive in the sense that the response robustly satisfies the intention of input utterance. At the same time the response must maintain coherence and relevance, regardless of the surface presentation. This means that response generation is constrained by the content of intentions, rather than the lexicons and grammar. Statistical techniques, mainly the over generation-and-ranking architecture works well in written language where sentence is the basic unit. However, in spoken language where utterance is the basic unit, the disadvantage becomes critical as spoken language also render intentions, hence short strings may be of equivalent impact. The bias towards shortstrings during ranking is the very limitation of this approach hence leading to our proposed intention-based classification-and-ranking architecture. In this architecture, response is deliberately chosen from dialogue corpus rather than wholly generated, such that it allows short ungrammatical utterances as long as they satisfy the intended meaning of input utterance. The architecture employs two basic components, which is a Bayesian classifier to classify user utterances into response classes based on their pragmatic interpretations, and an Entropic ranker that scores the candidate response utterances according to the semantic content relevant to the user utterance. The high-level, pragmatic knowledge in user utterances are used as features in Bayesian classification to constrain response utterance according to their contextual contributions, therefore, guiding our Maximum Entropy ranking process to find one single response utterance that is most relevant to the input utterance. The proposed architecture is tested on a mixed-initiative, transaction dialogue corpus of 64 conversations in theater information and reservation system. We measure the output of the intention-based response generation based on coherence of the response against the input utterance in the test set. We also tested the architecture on the second body of corpus in emergency planning to warrant the portability of architecture to cross domains. In the essence, intention-based response generation performs better as compared to surface generation because features used in the architecture extend well into pragmatics, beyond the linguistic forms and semantic interpretations. Conditioned response 2008-03 Thesis http://psasir.upm.edu.my/id/eprint/5894/ http://psasir.upm.edu.my/id/eprint/5894/1/FSKTM_2008_1%20IR.pdf text en public doctoral Universiti Putra Malaysia Conditioned response Computer Science and Information Technology Sulaiman, Md. Nasir
institution	Universiti Putra Malaysia
collection	PSAS Institutional Repository
language	English
advisor	Sulaiman, Md. Nasir
topic	Conditioned response
spellingShingle	Conditioned response Mustapha, Aida Classification-and-Ranking Architecture Based on Intentions for Response Generation Systems
description	Existing response generation accounts only concern with generation of words into sentences, either by means of grammar or statistical distribution. While the resulting utterance may be inarguably sophisticated, the impact may be not as forceful. We believe that the design for response generation requires more than grammar rules or some statistical distributions, but more intuitive in the sense that the response robustly satisfies the intention of input utterance. At the same time the response must maintain coherence and relevance, regardless of the surface presentation. This means that response generation is constrained by the content of intentions, rather than the lexicons and grammar. Statistical techniques, mainly the over generation-and-ranking architecture works well in written language where sentence is the basic unit. However, in spoken language where utterance is the basic unit, the disadvantage becomes critical as spoken language also render intentions, hence short strings may be of equivalent impact. The bias towards shortstrings during ranking is the very limitation of this approach hence leading to our proposed intention-based classification-and-ranking architecture. In this architecture, response is deliberately chosen from dialogue corpus rather than wholly generated, such that it allows short ungrammatical utterances as long as they satisfy the intended meaning of input utterance. The architecture employs two basic components, which is a Bayesian classifier to classify user utterances into response classes based on their pragmatic interpretations, and an Entropic ranker that scores the candidate response utterances according to the semantic content relevant to the user utterance. The high-level, pragmatic knowledge in user utterances are used as features in Bayesian classification to constrain response utterance according to their contextual contributions, therefore, guiding our Maximum Entropy ranking process to find one single response utterance that is most relevant to the input utterance. The proposed architecture is tested on a mixed-initiative, transaction dialogue corpus of 64 conversations in theater information and reservation system. We measure the output of the intention-based response generation based on coherence of the response against the input utterance in the test set. We also tested the architecture on the second body of corpus in emergency planning to warrant the portability of architecture to cross domains. In the essence, intention-based response generation performs better as compared to surface generation because features used in the architecture extend well into pragmatics, beyond the linguistic forms and semantic interpretations.
format	Thesis
qualification_level	Doctorate
author	Mustapha, Aida
author_facet	Mustapha, Aida
author_sort	Mustapha, Aida
title	Classification-and-Ranking Architecture Based on Intentions for Response Generation Systems
title_short	Classification-and-Ranking Architecture Based on Intentions for Response Generation Systems
title_full	Classification-and-Ranking Architecture Based on Intentions for Response Generation Systems
title_fullStr	Classification-and-Ranking Architecture Based on Intentions for Response Generation Systems
title_full_unstemmed	Classification-and-Ranking Architecture Based on Intentions for Response Generation Systems
title_sort	classification-and-ranking architecture based on intentions for response generation systems
granting_institution	Universiti Putra Malaysia
granting_department	Computer Science and Information Technology
publishDate	2008
url	http://psasir.upm.edu.my/id/eprint/5894/1/FSKTM_2008_1%20IR.pdf
_version_	1747810504270675968

Classification-and-Ranking Architecture Based on Intentions for Response Generation Systems

Similar Items