Summary of Action Controlled Paraphrasing, by Ning Shi et al.
Action Controlled Paraphrasing
by Ning Shi, Zijun Wu
First submitted to arxiv on: 18 May 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed setup for controlled paraphrase generation represents user intent as action tokens, which are embedded and concatenated with text embeddings before being fed into a self-attention encoder for representation fusion. This approach enables precise action-controlled paraphrasing and preserves or even enhances performance compared to conventional uncontrolled methods when actions are not given. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you want to rewrite some text in your own words, but you need specific instructions on how to do it. For example, you might want the rewritten text to be longer, shorter, more formal, or more casual. This paper explores ways to make machines generate paraphrased text that follows certain rules or guidelines. The researchers propose a new method that uses “action tokens” to specify what kind of rewriting is needed. They also find a way to make their approach work even when the user doesn’t provide specific instructions. |
Keywords
» Artificial intelligence » Encoder » Self attention
