Action Controlled Paraphrasing
Ning Shi, Zijun Wu

TL;DR
This paper introduces a novel approach to controlled paraphrase generation using action tokens, enabling user intent-driven paraphrasing without requiring detailed syntactic information, and addressing inference gaps.
Contribution
It proposes a new setup representing user intent as action tokens and introduces an optional placeholder to improve inference when actions are unspecified.
Findings
Effective action-controlled paraphrasing demonstrated
Model maintains performance without explicit actions
Promotes user-centered paraphrasing design
Abstract
Recent studies have demonstrated the potential to control paraphrase generation, such as through syntax, which has broad applications in various downstream tasks. However, these methods often require detailed parse trees or syntactic exemplars, countering human-like paraphrasing behavior in language use. Furthermore, an inference gap exists, as control specifications are only available during training but not during inference. In this work, we propose a new setup for controlled paraphrase generation. Specifically, we represent user intent as action tokens, embedding and concatenating them with text embeddings, thus flowing together into a self-attention encoder for representation fusion. To address the inference gap, we introduce an optional action token as a placeholder that encourages the model to determine the appropriate action independently when users' intended actions are not…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsText Readability and Simplification
