Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment

TL;DR

This paper introduces an unsupervised method for sentence-level paraphrasing using multiple-sequence alignment on unannotated corpora, resulting in accurate paraphrases that outperform baselines.

Contribution

It presents a novel unsupervised approach leveraging multiple-sequence alignment to learn paraphrasing patterns from unannotated data.

Findings

System derives accurate paraphrases

Outperforms baseline systems

Effective on unannotated comparable corpora

Abstract

We address the text-to-text generation problem of sentence-level paraphrasing -- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach applies multiple-sequence alignment to sentences gathered from unannotated comparable corpora: it learns a set of paraphrasing patterns represented by word lattice pairs and automatically determines how to apply these patterns to rewrite new sentences. The results of our evaluation experiments show that the system derives accurate paraphrases, outperforming baseline systems.