Energy-based Self-attentive Learning of Abstractive Communities for Spoken Language Understanding

Guokan Shang, Antoine Tixier, Michalis Vazirgiannis, Jean-Pierre Lorré


Abstract
Abstractive community detection is an important spoken language understanding task, whose goal is to group utterances in a conversation according to whether they can be jointly summarized by a common abstractive sentence. This paper provides a novel approach to this task. We first introduce a neural contextual utterance encoder featuring three types of self-attention mechanisms. We then train it using the siamese and triplet energy-based meta-architectures. Experiments on the AMI corpus show that our system outperforms multiple energy-based and non-energy based baselines from the state-of-the-art. Code and data are publicly available.
Anthology ID:
2020.aacl-main.34
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
Month:
December
Year:
2020
Address:
Suzhou, China
Venue:
AACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
313–327
Language:
URL:
https://aclanthology.org/2020.aacl-main.34
DOI:
Bibkey:
Cite (ACL):
Guokan Shang, Antoine Tixier, Michalis Vazirgiannis, and Jean-Pierre Lorré. 2020. Energy-based Self-attentive Learning of Abstractive Communities for Spoken Language Understanding. 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, pages 313–327, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Energy-based Self-attentive Learning of Abstractive Communities for Spoken Language Understanding (Shang et al., AACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.aacl-main.34.pdf
Code
 guokan_shang/abscomm