BiSECT: Learning to Split and Rephrase Sentences with Bitexts

Joongwon Kim, Mounica Maddela, Reno Kriz, Wei Xu, Chris Callison-Burch


Abstract
An important task in NLP applications such as sentence simplification is the ability to take a long, complex sentence and split it into shorter sentences, rephrasing as necessary. We introduce a novel dataset and a new model for this ‘split and rephrase’ task. Our BiSECT training data consists of 1 million long English sentences paired with shorter, meaning-equivalent English sentences. We obtain these by extracting 1-2 sentence alignments in bilingual parallel corpora and then using machine translation to convert both sides of the corpus into the same language. BiSECT contains higher quality training examples than the previous Split and Rephrase corpora, with sentence splits that require more significant modifications. We categorize examples in our corpus and use these categories in a novel model that allows us to target specific regions of the input sentence to be split and edited. Moreover, we show that models trained on BiSECT can perform a wider variety of split operations and improve upon previous state-of-the-art approaches in automatic and human evaluations.
Anthology ID:
2021.emnlp-main.500
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6193–6209
Language:
URL:
https://aclanthology.org/2021.emnlp-main.500
DOI:
10.18653/v1/2021.emnlp-main.500
Bibkey:
Cite (ACL):
Joongwon Kim, Mounica Maddela, Reno Kriz, Wei Xu, and Chris Callison-Burch. 2021. BiSECT: Learning to Split and Rephrase Sentences with Bitexts. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6193–6209, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
BiSECT: Learning to Split and Rephrase Sentences with Bitexts (Kim et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.500.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.500.mp4
Code
 mounicam/bisect
Data
BiSECT