Distantly Supervised Attribute Detection from Reviews

Lisheng Fu, Pablo Barrio


Abstract
This work aims to detect specific attributes of a place (e.g., if it has a romantic atmosphere, or if it offers outdoor seating) from its user reviews via distant supervision: without direct annotation of the review text, we use the crowdsourced attribute labels of the place as labels of the review text. We then use review-level attention to pay more attention to those reviews related to the attributes. The experimental results show that our attention-based model predicts attributes for places from reviews with over 98% accuracy. The attention weights assigned to each review provide explanation of capturing relevant reviews.
Anthology ID:
W18-6110
Volume:
Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text
Month:
November
Year:
2018
Address:
Brussels, Belgium
Editors:
Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
74–78
Language:
URL:
https://aclanthology.org/W18-6110
DOI:
10.18653/v1/W18-6110
Bibkey:
Cite (ACL):
Lisheng Fu and Pablo Barrio. 2018. Distantly Supervised Attribute Detection from Reviews. In Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text, pages 74–78, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Distantly Supervised Attribute Detection from Reviews (Fu & Barrio, WNUT 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6110.pdf