Abstract
This paper presents a deep neural architecture which applies the siamese convolutional neural network sharing model parameters for learning a semantic similarity metric between two sentences. In addition, two different similarity metrics (i.e., the Cosine Similarity and Manhattan similarity) are compared based on this architecture. Our experiments in binary similarity classification for Chinese sentence pairs show that the proposed siamese convolutional architecture with Manhattan similarity outperforms the baselines (i.e., the siamese Long Short-Term Memory architecture and the siamese Bidirectional Long Short-Term Memory architecture) by 8.7 points in accuracy.- Anthology ID:
- 2020.aacl-srw.4
- Volume:
- Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop
- Month:
- December
- Year:
- 2020
- Address:
- Suzhou, China
- Editors:
- Boaz Shmueli, Yin Jou Huang
- Venue:
- AACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 24–29
- Language:
- URL:
- https://aclanthology.org/2020.aacl-srw.4
- DOI:
- Cite (ACL):
- Haoxiang Shi, Cen Wang, and Tetsuya Sakai. 2020. A Siamese CNN Architecture for Learning Chinese Sentence Similarity. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 24–29, Suzhou, China. Association for Computational Linguistics.
- Cite (Informal):
- A Siamese CNN Architecture for Learning Chinese Sentence Similarity (Shi et al., AACL 2020)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2020.aacl-srw.4.pdf
- Data
- PAWS-X