Semantically Driven Sentence Fusion: Modeling and Evaluation

Eyal Ben-David, Orgad Keller, Eric Malmi, Idan Szpektor, Roi Reichart


Abstract
Sentence fusion is the task of joining related sentences into coherent text. Current training and evaluation schemes for this task are based on single reference ground-truths and do not account for valid fusion variants. We show that this hinders models from robustly capturing the semantic relationship between input sentences. To alleviate this, we present an approach in which ground-truth solutions are automatically expanded into multiple references via curated equivalence classes of connective phrases. We apply this method to a large-scale dataset and use the augmented dataset for both model training and evaluation. To improve the learning of semantic representation using multiple references, we enrich the model with auxiliary discourse classification tasks under a multi-tasking framework. Our experiments highlight the improvements of our approach over state-of-the-art models.
Anthology ID:
2020.findings-emnlp.135
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1491–1505
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.135
DOI:
10.18653/v1/2020.findings-emnlp.135
Bibkey:
Cite (ACL):
Eyal Ben-David, Orgad Keller, Eric Malmi, Idan Szpektor, and Roi Reichart. 2020. Semantically Driven Sentence Fusion: Modeling and Evaluation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1491–1505, Online. Association for Computational Linguistics.
Cite (Informal):
Semantically Driven Sentence Fusion: Modeling and Evaluation (Ben-David et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.135.pdf
Video:
 https://slideslive.com/38940063
Code
 eyalbd2/Semantically-Driven-Sentence-Fusion