Back to Basics for Monolingual Alignment: Exploiting Word Similarity and Contextual Evidence

Abstract

We present a simple, easy-to-replicate monolingual aligner that demonstrates state-of-the-art performance while relying on almost no supervision and a very small number of external resources. Based on the hypothesis that words with similar meanings represent potential pairs for alignment if located in similar contexts, we propose a system that operates by finding such pairs. In two intrinsic evaluations on alignment test data, our system achieves F1 scores of 88– 92%, demonstrating 1–3% absolute improvement over the previous best system. Moreover, in two extrinsic evaluations our aligner outperforms existing aligners, and even a naive application of the aligner approaches state-ofthe-art performance in each extrinsic task.

Extracted Key Phrases

8 Figures and Tables

020402014201520162017
Citations per Year

71 Citations

Semantic Scholar estimates that this publication has 71 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Sultan2014BackTB, title={Back to Basics for Monolingual Alignment: Exploiting Word Similarity and Contextual Evidence}, author={Md. Arafat Sultan and Steven Bethard and Tamara Sumner}, journal={TACL}, year={2014}, volume={2}, pages={219-230} }