Text Generation with Text-Editing Models

Eric Malmi, Yue Dong, Jonathan Mallinson, Aleksandr Chuklin, Jakub Adamek, Daniil Mirylenka, Felix Stahlberg, Sebastian Krause, Shankar Kumar, Aliaksei Severyn


Abstract
Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, text simplification, and style transfer. These tasks share a common trait – they exhibit a large amount of textual overlap between the source and target texts. Text-editing models take advantage of this observation and learn to generate the output by predicting edit operations applied to the source sequence. In contrast, seq2seq models generate outputs word-by-word from scratch thus making them slow at inference time. Text-editing models provide several benefits over seq2seq models including faster inference speed, higher sample efficiency, and better control and interpretability of the outputs. This tutorial provides a comprehensive overview of the text-edit based models and current state-of-the-art approaches analyzing their pros and cons. We discuss challenges related to deployment and how these models help to mitigate hallucination and bias, both pressing challenges in the field of text generation.
Anthology ID:
2022.naacl-tutorials.1
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorial Abstracts
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Miguel Ballesteros, Yulia Tsvetkov, Cecilia O. Alm
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–7
Language:
URL:
https://aclanthology.org/2022.naacl-tutorials.1
DOI:
10.18653/v1/2022.naacl-tutorials.1
Bibkey:
Cite (ACL):
Eric Malmi, Yue Dong, Jonathan Mallinson, Aleksandr Chuklin, Jakub Adamek, Daniil Mirylenka, Felix Stahlberg, Sebastian Krause, Shankar Kumar, and Aliaksei Severyn. 2022. Text Generation with Text-Editing Models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorial Abstracts, pages 1–7, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Text Generation with Text-Editing Models (Malmi et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-tutorials.1.pdf