SPARSE: Structured Prediction using Argument-Relative Structured Encoding

Rishi Bommasani, Arzoo Katiyar, Claire Cardie


Abstract
We propose structured encoding as a novel approach to learning representations for relations and events in neural structured prediction. Our approach explicitly leverages the structure of available relation and event metadata to generate these representations, which are parameterized by both the attribute structure of the metadata as well as the learned representation of the arguments of the relations and events. We consider affine, biaffine, and recurrent operators for building hierarchical representations and modelling underlying features. We apply our approach to the second-order structured prediction task studied in the 2016/2017 Belief and Sentiment analysis evaluations (BeSt): given a document and its entities, relations, and events (including metadata and mentions), determine the sentiment of each entity towards every relation and event in the document. Without task-specific knowledge sources or domain engineering, we significantly improve over systems and baselines that neglect the available metadata or its hierarchical structure. We observe across-the-board improvements on the BeSt 2016/2017 sentiment analysis task of at least 2.3 (absolute) and 10.6% (relative) F-measure over the previous state-of-the-art.
Anthology ID:
W19-1503
Volume:
Proceedings of the Third Workshop on Structured Prediction for NLP
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venues:
NAACL | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13–17
Language:
URL:
https://aclanthology.org/W19-1503
DOI:
10.18653/v1/W19-1503
Bibkey:
Cite (ACL):
Rishi Bommasani, Arzoo Katiyar, and Claire Cardie. 2019. SPARSE: Structured Prediction using Argument-Relative Structured Encoding. In Proceedings of the Third Workshop on Structured Prediction for NLP, pages 13–17, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
SPARSE: Structured Prediction using Argument-Relative Structured Encoding (Bommasani et al., 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-1503.pdf
Software:
 W19-1503.Software.zip
Supplementary:
 W19-1503.Supplementary.pdf