System Combination for Grammatical Error Correction Based on Integer Programming

TL;DR

This paper introduces a novel integer programming-based system combination method for grammatical error correction that optimizes error-type-specific F scores, leading to improved overall performance over individual systems.

Contribution

It presents a new IP-based approach for combining GEC systems, optimizing for error types, and demonstrates superior results compared to existing methods.

Findings

Outperforms standalone GEC systems in F0.5 score

Achieves a 3.61% improvement in F0.5 score on BEA 2019 data

Demonstrates competitive advantage over other system combination methods

Abstract

In this paper, we propose a system combination method for grammatical error correction (GEC), based on nonlinear integer programming (IP). Our method optimizes a novel F score objective based on error types, and combines multiple end-to-end GEC systems. The proposed IP approach optimizes the selection of a single best system for each grammatical error type present in the data. Experiments of the IP approach on combining state-of-the-art standalone GEC systems show that the combined system outperforms all standalone systems. It improves F0.5 score by 3.61% when combining the two best participating systems in the BEA 2019 shared task, and achieves F0.5 score of 73.08%. We also perform experiments to compare our IP approach with another state-of-the-art system combination method for GEC, demonstrating IP's competitive combination capability.