WEKO3
アイテム
Neuro or Symbolic? Fine-tuned Transformer with Unsupervised LDA Topic Clustering for Text Sentiment Analysis
https://tokushima-u.repo.nii.ac.jp/records/2011248
https://tokushima-u.repo.nii.ac.jp/records/20112480e8501a4-b2a1-4fb1-9dbe-36150f3407c1
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
taffc_15_2_493.pdf (2.07 MB)
Download is available from 2025/5/23.
|
|
| Item type | 文献 / Documents(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2023-10-11 | |||||||||||||
| アクセス権 | ||||||||||||||
| アクセス権 | embargoed access | |||||||||||||
| 資源タイプ | ||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||
| 資源タイプ | journal article | |||||||||||||
| 出版社版DOI | ||||||||||||||
| 識別子タイプ | DOI | |||||||||||||
| 関連識別子 | https://doi.org/10.1109/TAFFC.2023.3279318 | |||||||||||||
| 言語 | ja | |||||||||||||
| 関連名称 | 10.1109/TAFFC.2023.3279318 | |||||||||||||
| 出版タイプ | ||||||||||||||
| 出版タイプ | NA | |||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_be7fb7dd8ff6fe43 | |||||||||||||
| タイトル | ||||||||||||||
| タイトル | Neuro or Symbolic? Fine-tuned Transformer with Unsupervised LDA Topic Clustering for Text Sentiment Analysis | |||||||||||||
| 言語 | en | |||||||||||||
| 著者 |
Ding, Fei
× Ding, Fei
× 康, 鑫× 任, 福継
WEKO
401
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | For text sentiment analysis, state-of-the-art neural language models have demonstrated promising performance. However, they lack interpretability, require vast volumes of annotated data, and are typically specialized for tasks. In this paper, we explore a connection between fine-tuned Transformer models and unsupervised LDA approach to cope with text sentiment analysis tasks, inspired by the concept of Neuro-symbolic AI. The Transformer and LDA models are combined as a feature extractor to extract the hidden representations of the input text sequences. Subsequently, we employ a feedforward network to forecast various sentiment analysis tasks, such as multi-label emotion prediction, dialogue quality prediction, and nugget detection. Our proposed method obtains the best results in the NTCIR-16 dialogue evaluation (DialEval-2) task, as well as cutting-edge results in emotional intensity prediction using the Ren_CECps corpus. Extensive experiments show that our proposed method is highly explainable, cost-effective in training, and superior in terms of accuracy and robustness. | |||||||||||||
| 言語 | en | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Neuro-symbolic AI | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Sentiment Analysis | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Fine-tuned Transformer | |||||||||||||
| キーワード | ||||||||||||||
| 言語 | en | |||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Latent Dirichlet Allocation | |||||||||||||
| 書誌情報 |
en : IEEE Transactions on Affective Computing 巻 15, 号 2, p. 493-507, 発行日 2023-05-23 |
|||||||||||||
| 収録物ID | ||||||||||||||
| 収録物識別子タイプ | ISSN | |||||||||||||
| 収録物識別子 | 19493045 | |||||||||||||
| 出版者 | ||||||||||||||
| 出版者 | IEEE | |||||||||||||
| 言語 | en | |||||||||||||
| 権利情報 | ||||||||||||||
| 言語 | en | |||||||||||||
| 権利情報 | © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |||||||||||||
| EID | ||||||||||||||
| 識別子 | 396930 | |||||||||||||
| 識別子タイプ | URI | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
