Word-level Alignment for Multilingual Resource Acquisition
Abstract
We present a simple, one-pass word alignment algorithm for parallel text. Our algorithm utilizes synchronous parsing and takes advantage of existing syntactic annotations. In our experiments the performance of this model is comparable to more complicated iterative methods. We discuss the challenges and potential benefits of using the model to train syntactic parsers for new languages.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 2002
- Accession Number
- ADA458782
Entities
People
- Adam Lopez
- Michael Nossal
- Philip Resnik
- Rebecca Hwa
Organizations
- University of Maryland