NUS at the HOO 2012 Shared Task
نویسندگان
چکیده
This paper describes the submission of the National University of Singapore (NUS) to the HOO 2012 shared task. Our system uses a pipeline of confidence-weighted linear classifiers to correct determiner and preposition errors. Our system achieves the highest correction F1 score on the official test set among all 14 participating teams, based on gold-standard edits both before and after revision.
منابع مشابه
NUS at the HOO 2011 Pilot Shared Task
This paper describes the submission of the National University of Singapore (NUS) to the Helping Our Own (HOO) Pilot Shared Task. Our system targets spelling, article, and preposition errors in a sequential processing pipeline.
متن کاملKorea University System in the HOO 2012 Shared Task
In this paper, we describe the Korea University system that participated in the HOO 2012 Shared Task on the correction of preposition and determiner errors in non-native speaker texts. We focus our work on training the system on a large collection of error-tagged texts provided by the HOO 2012 Shared Task organizers and incrementally applying several methods to achieve better performance.
متن کاملHOO 2012 Shared Task: UKP Lab System Description
In this paper, we describe the UKP Lab system participating in the HOO 2012 Shared Task on preposition and determiner error correction. Our focus was to implement a highly flexible and modular system which can be easily augmented by other researchers. The system might be used to provide a level playground for subsequent shared tasks and enable further progress in this important research field o...
متن کاملInforming Determiner and Preposition Error Correction with Word Clusters
We extend our n-gram-based data-driven prediction approach from the Helping Our Own (HOO) 2011 Shared Task (Boyd and Meurers, 2011) to identify determiner and preposition errors in non-native English essays from the Cambridge Learner Corpus FCE Dataset (Yannakoudakis et al., 2011) as part of the HOO 2012 Shared Task. Our system focuses on three error categories: missing determiner, incorrect de...
متن کاملPrecision Isn't Everything: A Hybrid Approach to Grammatical Error Detection
Some grammatical error detection methods, including the ones currently used by the Educational Testing Service’s e-rater system (Attali and Burstein, 2006), are tuned for precision because of the perceived high cost of false positives (i.e., marking fluent English as ungrammatical). Precision, however, is not optimal for all tasks, particularly the HOO 2012 Shared Task on grammatical errors, wh...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012