Dynamic bayesian networks in Classification-and-Ranking Architecture of Response Generation
Problem statement: The first component in classification-and-ranking architecture is a Bayesian classifier that classifies user utterances into response classes based on their semantic and pragmatic interpretations. Bayesian networks are sufficient if data is limited to single user input utterance....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Science Publications.
2011
|
| Subjects: | |
| Online Access: | http://psasir.upm.edu.my/id/eprint/14160/ http://psasir.upm.edu.my/id/eprint/14160/1/Dynamic%20bayesian%20networks%20in%20Classification.pdf |
| _version_ | 1848842316348915712 |
|---|---|
| author | Mustapha, Aida Sulaiman, Md. Nasir Mahmod, Ramlan Selamat, Mohd Hasan |
| author_facet | Mustapha, Aida Sulaiman, Md. Nasir Mahmod, Ramlan Selamat, Mohd Hasan |
| author_sort | Mustapha, Aida |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Problem statement: The first component in classification-and-ranking architecture is a Bayesian classifier that classifies user utterances into response classes based on their semantic and pragmatic interpretations. Bayesian networks are sufficient if data is limited to single user input utterance. However, if the classifier is able to collate features from a sequence of previous n-1 user utterances, the additional information may or may not improve the accuracy rate in response classification. Approach: This article investigates the use of dynamic Bayesian networks to include time-series information in the form of extended features from preceding utterances. The experiment was conducted on SCHISMA corpus, which is a mixed-initiative, transaction dialogue in theater reservation. Results: The results show that classification accuracy is improved, but rather insignificantly. The accuracy rate tends to deteriorate as time-span of dialogue is increased. Conclusion: Although every response utterance reflects form and behavior that are expected by the preceding utterance, influence of meaning and intentions diminishes throughout time as the conversation stretches to longer duration. |
| first_indexed | 2025-11-15T07:57:12Z |
| format | Article |
| id | upm-14160 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English English |
| last_indexed | 2025-11-15T07:57:12Z |
| publishDate | 2011 |
| publisher | Science Publications. |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-141602015-10-16T08:43:20Z http://psasir.upm.edu.my/id/eprint/14160/ Dynamic bayesian networks in Classification-and-Ranking Architecture of Response Generation Mustapha, Aida Sulaiman, Md. Nasir Mahmod, Ramlan Selamat, Mohd Hasan Problem statement: The first component in classification-and-ranking architecture is a Bayesian classifier that classifies user utterances into response classes based on their semantic and pragmatic interpretations. Bayesian networks are sufficient if data is limited to single user input utterance. However, if the classifier is able to collate features from a sequence of previous n-1 user utterances, the additional information may or may not improve the accuracy rate in response classification. Approach: This article investigates the use of dynamic Bayesian networks to include time-series information in the form of extended features from preceding utterances. The experiment was conducted on SCHISMA corpus, which is a mixed-initiative, transaction dialogue in theater reservation. Results: The results show that classification accuracy is improved, but rather insignificantly. The accuracy rate tends to deteriorate as time-span of dialogue is increased. Conclusion: Although every response utterance reflects form and behavior that are expected by the preceding utterance, influence of meaning and intentions diminishes throughout time as the conversation stretches to longer duration. Science Publications. 2011 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/14160/1/Dynamic%20bayesian%20networks%20in%20Classification.pdf Mustapha, Aida and Sulaiman, Md. Nasir and Mahmod, Ramlan and Selamat, Mohd Hasan (2011) Dynamic bayesian networks in Classification-and-Ranking Architecture of Response Generation. Journal of Computer Science, 7 (1). pp. 59-64. ISSN 1549-3636 Bayesian statistical decision theory Neural networks (Computer science) Probabilities English |
| spellingShingle | Bayesian statistical decision theory Neural networks (Computer science) Probabilities Mustapha, Aida Sulaiman, Md. Nasir Mahmod, Ramlan Selamat, Mohd Hasan Dynamic bayesian networks in Classification-and-Ranking Architecture of Response Generation |
| title | Dynamic bayesian networks in Classification-and-Ranking Architecture of Response Generation |
| title_full | Dynamic bayesian networks in Classification-and-Ranking Architecture of Response Generation |
| title_fullStr | Dynamic bayesian networks in Classification-and-Ranking Architecture of Response Generation |
| title_full_unstemmed | Dynamic bayesian networks in Classification-and-Ranking Architecture of Response Generation |
| title_short | Dynamic bayesian networks in Classification-and-Ranking Architecture of Response Generation |
| title_sort | dynamic bayesian networks in classification-and-ranking architecture of response generation |
| topic | Bayesian statistical decision theory Neural networks (Computer science) Probabilities |
| url | http://psasir.upm.edu.my/id/eprint/14160/ http://psasir.upm.edu.my/id/eprint/14160/1/Dynamic%20bayesian%20networks%20in%20Classification.pdf |