Dialogue-Oriented Review Summary Generation for Spoken Dialogue Recommendation Systems
In this paper we present an opinion summarization technique in spoken dialogue systems. Opinion mining has been well studied for years, but very few have considered its application in spoken dialogue systems. Review summarization, when applied to real dialogue systems, is much more complicated than...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for Computational Linguistics
2011
|
| Online Access: | http://hdl.handle.net/1721.1/62575 https://orcid.org/0000-0003-2602-0862 https://orcid.org/0000-0001-8191-1049 |
| _version_ | 1826192000444006400 |
|---|---|
| author | Liu, Jingjing Seneff, Stephanie Zue, Victor |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Liu, Jingjing Seneff, Stephanie Zue, Victor |
| author_sort | Liu, Jingjing |
| collection | MIT |
| description | In this paper we present an opinion summarization technique in spoken dialogue systems. Opinion mining has been well studied for years, but very few have considered its application in spoken dialogue systems. Review summarization, when applied to real dialogue systems, is much more complicated than pure text-based summarization. We conduct a systematic study on dialogue-system-oriented review analysis and propose a three-level framework for a recommendation dialogue system. In previous work we have explored a linguistic parsing approach to phrase extraction from reviews. In this paper we will describe an approach using statistical models such as decision trees and SVMs to select the most representative phrases from the extracted phrase set. We will also explain how to generate informative yet concise review summaries for dialogue purposes. Experimental results in the restaurant domain show that the proposed approach using decision tree algorithms achieves an outperformance of 13% compared to SVM models and an improvement of 36% over a heuristic rule baseline. Experiments also show that the decision-tree-based phrase selection model can achieve rather reliable predictions on the phrase label, comparable to human judgment. The proposed statistical approach is based on domain-independent learning features and can be extended to other domains effectively. |
| first_indexed | 2024-09-23T09:04:39Z |
| format | Article |
| id | mit-1721.1/62575 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:04:39Z |
| publishDate | 2011 |
| publisher | Association for Computational Linguistics |
| record_format | dspace |
| spelling | mit-1721.1/625752022-09-26T10:16:09Z Dialogue-Oriented Review Summary Generation for Spoken Dialogue Recommendation Systems Liu, Jingjing Seneff, Stephanie Zue, Victor Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Zue, Victor Liu, Jingjing Seneff, Stephanie Zue, Victor In this paper we present an opinion summarization technique in spoken dialogue systems. Opinion mining has been well studied for years, but very few have considered its application in spoken dialogue systems. Review summarization, when applied to real dialogue systems, is much more complicated than pure text-based summarization. We conduct a systematic study on dialogue-system-oriented review analysis and propose a three-level framework for a recommendation dialogue system. In previous work we have explored a linguistic parsing approach to phrase extraction from reviews. In this paper we will describe an approach using statistical models such as decision trees and SVMs to select the most representative phrases from the extracted phrase set. We will also explain how to generate informative yet concise review summaries for dialogue purposes. Experimental results in the restaurant domain show that the proposed approach using decision tree algorithms achieves an outperformance of 13% compared to SVM models and an improvement of 36% over a heuristic rule baseline. Experiments also show that the decision-tree-based phrase selection model can achieve rather reliable predictions on the phrase label, comparable to human judgment. The proposed statistical approach is based on domain-independent learning features and can be extended to other domains effectively. 2011-05-02T17:48:08Z 2011-05-02T17:48:08Z 2010-06 2010-06 Article http://purl.org/eprint/type/ConferencePaper 1-932432-65-5 http://hdl.handle.net/1721.1/62575 Jingjing Liu, Stephanie Seneff, and Victor Zue. 2010. "Dialogue-oriented review summary generation for spoken dialogue recommendation systems." In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics (HLT '10). Association for Computational Linguistics, Stroudsburg, PA, USA, 64-72. https://orcid.org/0000-0003-2602-0862 https://orcid.org/0000-0001-8191-1049 en_US http://portal.acm.org/citation.cfm?id=1858007 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Association for Computational Linguistics MIT web domain |
| spellingShingle | Liu, Jingjing Seneff, Stephanie Zue, Victor Dialogue-Oriented Review Summary Generation for Spoken Dialogue Recommendation Systems |
| title | Dialogue-Oriented Review Summary Generation for Spoken Dialogue Recommendation Systems |
| title_full | Dialogue-Oriented Review Summary Generation for Spoken Dialogue Recommendation Systems |
| title_fullStr | Dialogue-Oriented Review Summary Generation for Spoken Dialogue Recommendation Systems |
| title_full_unstemmed | Dialogue-Oriented Review Summary Generation for Spoken Dialogue Recommendation Systems |
| title_short | Dialogue-Oriented Review Summary Generation for Spoken Dialogue Recommendation Systems |
| title_sort | dialogue oriented review summary generation for spoken dialogue recommendation systems |
| url | http://hdl.handle.net/1721.1/62575 https://orcid.org/0000-0003-2602-0862 https://orcid.org/0000-0001-8191-1049 |
| work_keys_str_mv | AT liujingjing dialogueorientedreviewsummarygenerationforspokendialoguerecommendationsystems AT seneffstephanie dialogueorientedreviewsummarygenerationforspokendialoguerecommendationsystems AT zuevictor dialogueorientedreviewsummarygenerationforspokendialoguerecommendationsystems |