Abstract
Recently, large language models such as GPT-2 have shown themselves to be extremely adept at text generation and have also been able to achieve high-quality results in many downstream NLP tasks such as text classification, sentiment analysis and question answering with the aid of fine-tuning. We present a useful technique for using a large language model to perform the task of paraphrasing on a variety of texts and subjects. Our approach is demonstrated to be capable of generating paraphrases not only at a sentence level but also for longer spans of text such as paragraphs without needing to break the text into smaller chunks.- Anthology ID:
- D19-5623
- Volume:
- Proceedings of the 3rd Workshop on Neural Generation and Translation
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong
- Venue:
- NGT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 215–220
- Language:
- URL:
- https://aclanthology.org/D19-5623
- DOI:
- 10.18653/v1/D19-5623
- Cite (ACL):
- Sam Witteveen and Martin Andrews. 2019. Paraphrasing with Large Language Models. In Proceedings of the 3rd Workshop on Neural Generation and Translation, pages 215–220, Hong Kong. Association for Computational Linguistics.
- Cite (Informal):
- Paraphrasing with Large Language Models (Witteveen & Andrews, NGT 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/D19-5623.pdf
- Data
- WebText