Don’t Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models

Mahnaz Koupaee, Greg Durrett, Nathanael Chambers, Niranjan Balasubramanian


Abstract
Event language models represent plausible sequences of events. Most existing approaches train autoregressive models on text, which successfully capture event co-occurrence but unfortunately constrain the model to follow the discourse order in which events are presented. Other domains may employ different discourse orders, and for many applications, we may care about different notions of ordering (e.g., temporal) or not care about ordering at all (e.g., when predicting related events in a schema). We propose a simple yet surprisingly effective strategy for improving event language models by perturbing event sequences so we can relax model dependence on text order. Despite generating completely synthetic event orderings, we show that this technique improves the performance of the event language models on both applications and out-of-domain events data.
Anthology ID:
2021.acl-short.76
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
599–604
Language:
URL:
https://aclanthology.org/2021.acl-short.76
DOI:
10.18653/v1/2021.acl-short.76
Bibkey:
Cite (ACL):
Mahnaz Koupaee, Greg Durrett, Nathanael Chambers, and Niranjan Balasubramanian. 2021. Don’t Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 599–604, Online. Association for Computational Linguistics.
Cite (Informal):
Don’t Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models (Koupaee et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.76.pdf
Video:
 https://aclanthology.org/2021.acl-short.76.mp4