Correcting verb selection errors for ESL with the perceptron

Authors:
Xiaohua Liu;Bo Han;Ming Zhou
Affiliations:
School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China and Microsoft Research Asia, Beijing, China;Department of Computer Science and Software Engineering, The University of Melbourne, Victoria, Australia;Microsoft Research Asia, Beijing, China
Venue:
CICLing'11 Proceedings of the 12th international conference on Computational linguistics and intelligent text processing - Volume Part II
Year:
2011

Citing 7
Cited 0

An intelligent tutoring system for deaf learners of written English

Assets '00 Proceedings of the fourth international ACM conference on Assistive technologies
Handbook of Natural Language Processing

Handbook of Natural Language Processing
Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms

EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Correcting ESL errors using phrasal SMT techniques

ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Hierarchical Phrase-Based Translation

Computational Linguistics
The ups and downs of preposition error detection in ESL writing

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
SRL-based verb selection for ESL

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study the task of correcting verb selection errors for English as a Second Language (ESL) learners, which is meaningful but also challenging. The difficulties of this task lie in two aspects: the lack of annotated data and the diversity of verb usage context. We propose a perceptron based novel approach to this task. More specifically, our method generates correction candidates using predefined confusion sets, to avoid the tedious and prohibitively unaffordable human labeling; moreover, rich linguistic features are integrated to represent verb usage context, using a global linear model learnt by the perceptron algorithm. The features used in our method include a language model, local text, chunks, and semantic collocations. Our method is evaluated on both synthetic and real-world corpora, and consistently achieves encouraging results, outperforming all baselines.