NAIST at 2013 CoNLL Grammatical Error Correction Shared Task
نویسندگان
چکیده
This paper describes the Nara Institute of Science and Technology (NAIST) error correction system in the CoNLL 2013 Shared Task. We constructed three systems: a system based on the Treelet Language Model for verb form and subjectverb agreement errors; a classifier trained on both learner and native corpora for noun number errors; a statistical machine translation (SMT)-based model for preposition and determiner errors. As for subject-verb agreement errors, we show that the Treelet Language Model-based approach can correct errors in which the target verb is distant from its subject. Our system ranked fourth on the official run.
منابع مشابه
CoNLL-2013 Shared Task: Grammatical Error Correction NTHU System Description
Grammatical error correction has been an active research area in the field of Natural Language Processing. This paper describes the grammatical error correction system developed at NTHU in participation of the CoNLL-2013 Shared Task. The system consists of four modules in a pipeline to correct errors related to determiners, prepositions, verb forms and noun number. Although more types of errors...
متن کاملThe CoNLL-2013 Shared Task on Grammatical Error Correction
The CoNLL-2013 shared task was devoted to grammatical error correction. In this paper, we give the task definition, present the data sets, and describe the evaluation metric and scorer used in the shared task. We also give an overview of the various approaches adopted by the participating teams, and present the evaluation results.
متن کاملKUNLP Grammatical Error Correction System For CoNLL-2013 Shared Task
This paper describes an English grammatical error correction system for CoNLL2013 shared task. Error types covered by our system are article/determiner, preposition, and noun number agreement. This work is our first attempt on grammatical error correction research. In this work, we only focus on reimplementing the techniques presented before and optimizing the performance. As a result of the im...
متن کاملGrammatical Error Correction as Multiclass Classification with Single Model
This paper describes our system in the shared task of CoNLL-2013. We illustrate that grammatical error detection and correction can be transformed into a multiclass classification task and implemented as a single-model system regardless of various error types with the aid of maximum entropy modeling. Our system achieves the F1 score of 17.13% on the standard test set.
متن کاملThe CoNLL-2014 Shared Task on Grammatical Error Correction
The CoNLL-2014 shared task was devoted to grammatical error correction of all error types. In this paper, we give the task definition, present the data sets, and describe the evaluation metric and scorer used in the shared task. We also give an overview of the various approaches adopted by the participating teams, and present the evaluation results. Compared to the CoNLL2013 shared task, we hav...
متن کامل