The UI System in the HOO 2012 Shared Task on Error Correction

We describe the University of Illinois (UI) system that participated in the Helping Our Own (HOO) 2012 shared task, which focuses on correcting preposition and determiner errors made by non-native English speakers. The task consisted of three metrics: Detection, Recognition, and Correction, and measured performance before and after additional revisions to the test data were made. Out of 14 teams that participated, our system scored first in Detection and Recognition and second in Correction before the revisions; and first in Detection and second in the other metrics after revisions. We describe our underlying approach, which relates to our previous work in this area, and propose an improvement to the earlier method, error inflation, which results in significant gains in performance.

[1]  Dan Roth,et al.  Applying Winnow to Context-Sensitive Spelling Correction , 1996, ICML.

[2]  Yoav Freund,et al.  Large Margin Classification Using the Perceptron Algorithm , 1998, COLT' 98.

[3]  Dan Roth,et al.  The Use of Classifiers in Sequential Inference , 2001, NIPS.

[4]  Dan Roth,et al.  Scaling Up Context-Sensitive Text Correction , 2001, IAAI.

[5]  Michele Banko,et al.  Scaling to Very Very Large Corpora for Natural Language Disambiguation , 2001, ACL.

[6]  Dan Roth,et al.  A Winnow-Based Approach to Context-Sensitive Spelling Correction , 1998, Machine Learning.

[7]  N. A-R A E H A N,et al.  Detecting errors in English article usage by non-native speakers , 2006 .

[8]  Andrew Carlson,et al.  Memory-based context-sensitive spelling correction at web scale , 2007, ICMLA 2007.

[9]  Andrew Carlson,et al.  Memory-based context-sensitive spelling correction at web scale , 2007, Sixth International Conference on Machine Learning and Applications (ICMLA 2007).

[10]  Stephanie Seneff,et al.  An analysis of grammatical errors in non-native speech in english , 2008, 2008 IEEE Spoken Language Technology Workshop.

[11]  Dan Roth,et al.  Generating Confusion Sets for Context-Sensitive Error Correction , 2010, EMNLP.

[12]  Michael Gamon,et al.  Using Mostly Native Data to Correct Errors in Learners’ Writing , 2010, NAACL.

[13]  Na-Rae Han,et al.  Using an Error-Annotated Learner Corpus to Develop an ESL/EFL Error Correction System , 2010, LREC.

[14]  Dan Roth,et al.  Training Paradigms for Correcting Errors in Grammar and Usage , 2010, NAACL.

[15]  Dan Roth,et al.  Learning Based Java for Rapid Development of NLP Systems , 2010, LREC.

[16]  Dan Roth,et al.  Annotating ESL Errors: Challenges and Rewards , 2010 .

[17]  Hwee Tou Ng,et al.  Grammatical Error Correction with Alternating Structure Optimization , 2011, ACL.

[18]  Dan Roth,et al.  Algorithm Selection and Model Adaptation for ESL Correction Tasks , 2011, ACL.

[19]  Helen Yannakoudakis,et al.  A New Dataset and Method for Automatically Grading ESOL Texts , 2011, ACL.

[20]  Dan Roth,et al.  University of Illinois System in HOO Text Correction Shared Task , 2011, ENLG.

[21]  Adam Kilgarriff,et al.  Helping Our Own: The HOO 2011 Pilot Shared Task , 2011, ENLG.

[22]  Robert Dale,et al.  HOO 2012: A Report on the Preposition and Determiner Error Correction Shared Task , 2012, BEA@NAACL-HLT.

[23]  Claudia Leacock,et al.  Automated Grammatical Error Correction for Language Learners , 2010, COLING.