Deep Weighted MaxSAT for Aspect-based Opinion Extraction

Meixi Wu, Wenya Wang, Sinno Jialin Pan


Abstract
Though deep learning has achieved significant success in various NLP tasks, most deep learning models lack the capability of encoding explicit domain knowledge to model complex causal relationships among different types of variables. On the other hand, logic rules offer a compact expression to represent the causal relationships to guide the training process. Logic programs can be cast as a satisfiability problem which aims to find truth assignments to logic variables by maximizing the number of satisfiable clauses (MaxSAT). We adopt the MaxSAT semantics to model logic inference process and smoothly incorporate a weighted version of MaxSAT that connects deep neural networks and a graphical model in a joint framework. The joint model feeds deep learning outputs to a weighted MaxSAT layer to rectify the erroneous predictions and can be trained via end-to-end gradient descent. Our proposed model associates the benefits of high-level feature learning, knowledge reasoning, and structured learning with observable performance gain for the task of aspect-based opinion extraction.
Anthology ID:
2020.emnlp-main.453
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5618–5628
Language:
URL:
https://aclanthology.org/2020.emnlp-main.453
DOI:
10.18653/v1/2020.emnlp-main.453
Bibkey:
Cite (ACL):
Meixi Wu, Wenya Wang, and Sinno Jialin Pan. 2020. Deep Weighted MaxSAT for Aspect-based Opinion Extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5618–5628, Online. Association for Computational Linguistics.
Cite (Informal):
Deep Weighted MaxSAT for Aspect-based Opinion Extraction (Wu et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.453.pdf
Video:
 https://slideslive.com/38939342