Improving the Performance of Answers Ranking in Q&A Communities: A Long-Text Matching Technique and Pre-Trained Model
This paper introduces TR-BERT, a novel method to answer ranking in Question & Answer (Q&A) communities, designed to tackle the widespread challenges of irrelevant popular answers and the neglect of new questions. TR-BERT integrates a long-text matching technique with a pre-trai...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10813354/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550850977169408 |
|---|---|
| author | Siyu Sun Yiming Wang Jiale Cheng Zhiying Xiao Daqing Zheng Xiaoling Hao |
| author_facet | Siyu Sun Yiming Wang Jiale Cheng Zhiying Xiao Daqing Zheng Xiaoling Hao |
| author_sort | Siyu Sun |
| collection | DOAJ |
| description | This paper introduces TR-BERT, a novel method to answer ranking in Question & Answer (Q&A) communities, designed to tackle the widespread challenges of irrelevant popular answers and the neglect of new questions. TR-BERT integrates a long-text matching technique with a pre-trained language model. This ranking method effectively filters the noise and extracts textual features of questions and answers in QA communities. The experimental results on the Zhihu Q&A community dataset and the SemEval-2017 dataset showed the effectiveness and superiority of the TR-BERT. The contributions are as follows: Designing a new framework to process long-text data by filtering the noise and developing the TR-BERT to optimize the issue of answer ranking in the Q&A community. The experiment also showed that the TR-BERT model has the advantages of faster speed and requires less computational resources, which makes the TR-BERT valuable for practical applications. Meanwhile, TR-BERT offers an insight: By removing noise from the input text to shorten the length of the input sequence, we can decrease the time and computational resources required for model training and computation. This leads to the potential for smaller models, faster speeds, reduced computational resource demands, and improved efficiency. |
| format | Article |
| id | doaj-art-716e846e0c53417c98eb6defbf60a93e |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-716e846e0c53417c98eb6defbf60a93e2025-01-10T00:00:50ZengIEEEIEEE Access2169-35362025-01-01134188420010.1109/ACCESS.2024.352199910813354Improving the Performance of Answers Ranking in Q&A Communities: A Long-Text Matching Technique and Pre-Trained ModelSiyu Sun0Yiming Wang1https://orcid.org/0000-0002-6385-0198Jiale Cheng2Zhiying Xiao3https://orcid.org/0009-0001-9278-0563Daqing Zheng4https://orcid.org/0000-0002-4202-8074Xiaoling Hao5Shanghai University of Finance and Economics Zhejiang College, Jinhua, Zhejiang, ChinaSchool of Information Management Engineering, Shanghai University of Finance and Economics, Shanghai, ChinaSchool of Information Management Engineering, Shanghai University of Finance and Economics, Shanghai, ChinaShanghai University of Finance and Economics Zhejiang College, Jinhua, Zhejiang, ChinaSchool of Information Management Engineering, Shanghai University of Finance and Economics, Shanghai, ChinaSchool of Information Management Engineering, Shanghai University of Finance and Economics, Shanghai, ChinaThis paper introduces TR-BERT, a novel method to answer ranking in Question & Answer (Q&A) communities, designed to tackle the widespread challenges of irrelevant popular answers and the neglect of new questions. TR-BERT integrates a long-text matching technique with a pre-trained language model. This ranking method effectively filters the noise and extracts textual features of questions and answers in QA communities. The experimental results on the Zhihu Q&A community dataset and the SemEval-2017 dataset showed the effectiveness and superiority of the TR-BERT. The contributions are as follows: Designing a new framework to process long-text data by filtering the noise and developing the TR-BERT to optimize the issue of answer ranking in the Q&A community. The experiment also showed that the TR-BERT model has the advantages of faster speed and requires less computational resources, which makes the TR-BERT valuable for practical applications. Meanwhile, TR-BERT offers an insight: By removing noise from the input text to shorten the length of the input sequence, we can decrease the time and computational resources required for model training and computation. This leads to the potential for smaller models, faster speeds, reduced computational resource demands, and improved efficiency.https://ieeexplore.ieee.org/document/10813354/Q&A communityanswer rankingTR-BERTdeep neural network |
| spellingShingle | Siyu Sun Yiming Wang Jiale Cheng Zhiying Xiao Daqing Zheng Xiaoling Hao Improving the Performance of Answers Ranking in Q&A Communities: A Long-Text Matching Technique and Pre-Trained Model IEEE Access Q&A community answer ranking TR-BERT deep neural network |
| title | Improving the Performance of Answers Ranking in Q&A Communities: A Long-Text Matching Technique and Pre-Trained Model |
| title_full | Improving the Performance of Answers Ranking in Q&A Communities: A Long-Text Matching Technique and Pre-Trained Model |
| title_fullStr | Improving the Performance of Answers Ranking in Q&A Communities: A Long-Text Matching Technique and Pre-Trained Model |
| title_full_unstemmed | Improving the Performance of Answers Ranking in Q&A Communities: A Long-Text Matching Technique and Pre-Trained Model |
| title_short | Improving the Performance of Answers Ranking in Q&A Communities: A Long-Text Matching Technique and Pre-Trained Model |
| title_sort | improving the performance of answers ranking in q x0026 a communities a long text matching technique and pre trained model |
| topic | Q&A community answer ranking TR-BERT deep neural network |
| url | https://ieeexplore.ieee.org/document/10813354/ |
| work_keys_str_mv | AT siyusun improvingtheperformanceofanswersrankinginqx0026acommunitiesalongtextmatchingtechniqueandpretrainedmodel AT yimingwang improvingtheperformanceofanswersrankinginqx0026acommunitiesalongtextmatchingtechniqueandpretrainedmodel AT jialecheng improvingtheperformanceofanswersrankinginqx0026acommunitiesalongtextmatchingtechniqueandpretrainedmodel AT zhiyingxiao improvingtheperformanceofanswersrankinginqx0026acommunitiesalongtextmatchingtechniqueandpretrainedmodel AT daqingzheng improvingtheperformanceofanswersrankinginqx0026acommunitiesalongtextmatchingtechniqueandpretrainedmodel AT xiaolinghao improvingtheperformanceofanswersrankinginqx0026acommunitiesalongtextmatchingtechniqueandpretrainedmodel |