Query-focused Scenario Construction

Su Wang, Greg Durrett, Katrin Erk


Abstract
The news coverage of events often contains not one but multiple incompatible accounts of what happened. We develop a query-based system that extracts compatible sets of events (scenarios) from such data, formulated as one-class clustering. Our system incrementally evaluates each event’s compatibility with already selected events, taking order into account. We use synthetic data consisting of article mixtures for scalable training and evaluate our model on a new human-curated dataset of scenarios about real-world news topics. Stronger neural network models and harder synthetic training settings are both important to achieve high performance, and our final scenario construction system substantially outperforms baselines based on prior work.
Anthology ID:
D19-1273
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2712–2722
Language:
URL:
https://aclanthology.org/D19-1273
DOI:
10.18653/v1/D19-1273
Bibkey:
Cite (ACL):
Su Wang, Greg Durrett, and Katrin Erk. 2019. Query-focused Scenario Construction. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2712–2722, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Query-focused Scenario Construction (Wang et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1273.pdf