Genetic-based approach for cue phrase selection in dialogue act recognition
Automatic cue phrase selection is a crucial step for designing a dialogue act recognition model using machine learning techniques. The approaches, currently used, are based on specific type of feature selection approaches, called ranking approaches. Despite their computational efficiency for high di...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2009
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/14882/ http://psasir.upm.edu.my/id/eprint/14882/1/Genetic-based%20approach%20for%20cue%20phrase%20selection%20in%20dialogue%20act%20recognition.pdf |
| _version_ | 1848842521732448256 |
|---|---|
| author | Yahya, Anwar Ali Ramli, Abdul Rahman |
| author_facet | Yahya, Anwar Ali Ramli, Abdul Rahman |
| author_sort | Yahya, Anwar Ali |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Automatic cue phrase selection is a crucial step for designing a dialogue act recognition model using machine learning techniques. The approaches, currently used, are based on specific type of feature selection approaches, called ranking approaches. Despite their computational efficiency for high dimensional domains, they are not optimal with respect to relevance and redundancy. In this paper we propose a genetic-based approach for cue phrase selection which is, essentially, a variable length genetic algorithm developed to cope with the high dimensionality of the domain. We evaluate the performance of the proposed approach against several ranking approaches. Additionally, we assess its performance for the selection of cue phrases enriched by phrase’s type and phrase’s position. The results provide experimental evidences on the ability of the genetic-based approach to handle the drawbacks of the ranking approaches and to exploit cue’s type and cue’s position information to improve the selection. Furthermore, we validate the use of the genetic-based approach for machine learning applications. We use selected sets of cue phrases for building a dynamic Bayesian networks model for dialogue act recognition. The results show its usefulness for machine learning applications. |
| first_indexed | 2025-11-15T08:00:27Z |
| format | Article |
| id | upm-14882 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T08:00:27Z |
| publishDate | 2009 |
| publisher | Springer |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-148822019-05-08T07:28:03Z http://psasir.upm.edu.my/id/eprint/14882/ Genetic-based approach for cue phrase selection in dialogue act recognition Yahya, Anwar Ali Ramli, Abdul Rahman Automatic cue phrase selection is a crucial step for designing a dialogue act recognition model using machine learning techniques. The approaches, currently used, are based on specific type of feature selection approaches, called ranking approaches. Despite their computational efficiency for high dimensional domains, they are not optimal with respect to relevance and redundancy. In this paper we propose a genetic-based approach for cue phrase selection which is, essentially, a variable length genetic algorithm developed to cope with the high dimensionality of the domain. We evaluate the performance of the proposed approach against several ranking approaches. Additionally, we assess its performance for the selection of cue phrases enriched by phrase’s type and phrase’s position. The results provide experimental evidences on the ability of the genetic-based approach to handle the drawbacks of the ranking approaches and to exploit cue’s type and cue’s position information to improve the selection. Furthermore, we validate the use of the genetic-based approach for machine learning applications. We use selected sets of cue phrases for building a dynamic Bayesian networks model for dialogue act recognition. The results show its usefulness for machine learning applications. Springer 2009 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/14882/1/Genetic-based%20approach%20for%20cue%20phrase%20selection%20in%20dialogue%20act%20recognition.pdf Yahya, Anwar Ali and Ramli, Abdul Rahman (2009) Genetic-based approach for cue phrase selection in dialogue act recognition. Evolutionary Intelligence, 1 (4). pp. 253-269. ISSN 1864-5909; ESSN: 1864-5917 https://link.springer.com/article/10.1007/s12065-008-0016-6#enumeration 10.1007/s12065-008-0016-6 |
| spellingShingle | Yahya, Anwar Ali Ramli, Abdul Rahman Genetic-based approach for cue phrase selection in dialogue act recognition |
| title | Genetic-based approach for cue phrase selection in dialogue act recognition |
| title_full | Genetic-based approach for cue phrase selection in dialogue act recognition |
| title_fullStr | Genetic-based approach for cue phrase selection in dialogue act recognition |
| title_full_unstemmed | Genetic-based approach for cue phrase selection in dialogue act recognition |
| title_short | Genetic-based approach for cue phrase selection in dialogue act recognition |
| title_sort | genetic-based approach for cue phrase selection in dialogue act recognition |
| url | http://psasir.upm.edu.my/id/eprint/14882/ http://psasir.upm.edu.my/id/eprint/14882/ http://psasir.upm.edu.my/id/eprint/14882/ http://psasir.upm.edu.my/id/eprint/14882/1/Genetic-based%20approach%20for%20cue%20phrase%20selection%20in%20dialogue%20act%20recognition.pdf |