Work

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

Year: 2014

Type: article

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-of-the-art performance in each extrinsic task.

Source: Transactions of the Association for Computational Linguistics

DOI: 10.1162/tacl_a_00178

Authors: Md Arafat Sultan, Steven Bethard, Tamara Sumner

Institutions: University of Colorado Boulder, University of Colorado System, University of Alabama at Birmingham

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funder: National Science Foundation

Awards: Collaborative Research: Enabling Robust Learning with Conceptual Personalization Technologies, Collaborative Research: Enabling Robust Learning with Conceptual Personalization Technologies