Extracting Structural Paraphrases from Aligned Monolingual Corpora
Abstract
We present an approach for automatically learning paraphrases from aligned monolingual corpora. Our algorithm works by generalizing the syntactic paths between corresponding anchors in aligned sentence pairs. Compared to previous work, structural paraphrases generated by our algorithm tend to be much longer on average, and are capable of capturing long-distance dependencies. In addition to a standalone evaluation of our paraphrases, we also describe a question answering application currently under development that could immensely benefit from automatically-learned structural paraphrases. for large-scale applications, attention has recently focused on techniques for automatically acquiring paraphrases. We present an unsupervised method for acquiring structural paraphrases,
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2003
- Accession Number
- ADA460577
Entities
People
- Ali Ibrahim
- Boris Katz
- Jimmy Lin
Organizations
- Massachusetts Institute of Technology