A matching model for culture and tourism customer service questions based on domain dictionary fusion
In culture and tourism intelligent question answering, the sparse representation, colloquial expression, polysemy of a word, and difficulty in recognizing specific domain vocabulary make it difficult for common matching models to accurately match user questions with standard questions. In response t...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of XPU
2024-06-01
|
| Series: | Xi'an Gongcheng Daxue xuebao |
| Subjects: | |
| Online Access: | http://journal.xpu.edu.cn/en/#/digest?ArticleID=1473 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849727328812269568 |
|---|---|
| author | ZHU Xinjuan NIU Tingting |
| author_facet | ZHU Xinjuan NIU Tingting |
| author_sort | ZHU Xinjuan |
| collection | DOAJ |
| description | In culture and tourism intelligent question answering, the sparse representation, colloquial expression, polysemy of a word, and difficulty in recognizing specific domain vocabulary make it difficult for common matching models to accurately match user questions with standard questions. In response to this issue, firstly a dataset of customer service question matching for cultural and tourism and corresponding domain dictionaries were constructed. Then a cultural and tourism question matching model SBIDD (Improved SBERT Model for Integrating Domain Dictionaries) integrating domain dictionaries was proposed. The model utilizes SBERT to vectorize questions and incorporates a domain dictionary into the twin network model to enhance the domain word weight of the questions, greatly improving it′s ability to recognize domain vocabulary. Experiments were conducted on both self-built dataset and the public dataset ATEC 2018 NLP. The results show that compared with the classic text matching models such as DSSM, BiMPM, ESIM, IMAF, TSFR-RM, and baseline model SBERT, SBIDD has better performance, with F1 value reaching 95.65%, an increase of 2.75% compared to the baseline model, and shows higher adaptability and robustness in retrieval tasks. |
| format | Article |
| id | doaj-art-ee59b0adffd74499bc8721498928cfdb |
| institution | DOAJ |
| issn | 1674-649X |
| language | zho |
| publishDate | 2024-06-01 |
| publisher | Editorial Office of Journal of XPU |
| record_format | Article |
| series | Xi'an Gongcheng Daxue xuebao |
| spelling | doaj-art-ee59b0adffd74499bc8721498928cfdb2025-08-20T03:09:52ZzhoEditorial Office of Journal of XPUXi'an Gongcheng Daxue xuebao1674-649X2024-06-01383929910.13338/j.issn.1674-649x.2024.03.013A matching model for culture and tourism customer service questions based on domain dictionary fusionZHU Xinjuan0NIU Tingting1School of Computer Science/The Shaanxi Key Laboratory of Clothing Intelligence, Xi’an Polytechnic University, Xi’an 710600, ChinaSchool of Computer Science/The Shaanxi Key Laboratory of Clothing Intelligence, Xi’an Polytechnic University, Xi’an 710600, ChinaIn culture and tourism intelligent question answering, the sparse representation, colloquial expression, polysemy of a word, and difficulty in recognizing specific domain vocabulary make it difficult for common matching models to accurately match user questions with standard questions. In response to this issue, firstly a dataset of customer service question matching for cultural and tourism and corresponding domain dictionaries were constructed. Then a cultural and tourism question matching model SBIDD (Improved SBERT Model for Integrating Domain Dictionaries) integrating domain dictionaries was proposed. The model utilizes SBERT to vectorize questions and incorporates a domain dictionary into the twin network model to enhance the domain word weight of the questions, greatly improving it′s ability to recognize domain vocabulary. Experiments were conducted on both self-built dataset and the public dataset ATEC 2018 NLP. The results show that compared with the classic text matching models such as DSSM, BiMPM, ESIM, IMAF, TSFR-RM, and baseline model SBERT, SBIDD has better performance, with F1 value reaching 95.65%, an increase of 2.75% compared to the baseline model, and shows higher adaptability and robustness in retrieval tasks.http://journal.xpu.edu.cn/en/#/digest?ArticleID=1473question matchingculture and tourism customer servicesentence-bertdomain dictionaryintelligent question and answersearch based q&a |
| spellingShingle | ZHU Xinjuan NIU Tingting A matching model for culture and tourism customer service questions based on domain dictionary fusion Xi'an Gongcheng Daxue xuebao question matching culture and tourism customer service sentence-bert domain dictionary intelligent question and answer search based q&a |
| title | A matching model for culture and tourism customer service questions based on domain dictionary fusion |
| title_full | A matching model for culture and tourism customer service questions based on domain dictionary fusion |
| title_fullStr | A matching model for culture and tourism customer service questions based on domain dictionary fusion |
| title_full_unstemmed | A matching model for culture and tourism customer service questions based on domain dictionary fusion |
| title_short | A matching model for culture and tourism customer service questions based on domain dictionary fusion |
| title_sort | matching model for culture and tourism customer service questions based on domain dictionary fusion |
| topic | question matching culture and tourism customer service sentence-bert domain dictionary intelligent question and answer search based q&a |
| url | http://journal.xpu.edu.cn/en/#/digest?ArticleID=1473 |
| work_keys_str_mv | AT zhuxinjuan amatchingmodelforcultureandtourismcustomerservicequestionsbasedondomaindictionaryfusion AT niutingting amatchingmodelforcultureandtourismcustomerservicequestionsbasedondomaindictionaryfusion AT zhuxinjuan matchingmodelforcultureandtourismcustomerservicequestionsbasedondomaindictionaryfusion AT niutingting matchingmodelforcultureandtourismcustomerservicequestionsbasedondomaindictionaryfusion |