A Beam-Search Decoder for Grammatical Error Correction (12155N)
IDA Technology Roadmap 2012
This technology falls in the following categories of Singapore's IDA Infocomm Technology Roadmap 2012:
For more information on this technology contact:
This invention is a method for automatic correction of grammatical errors made in written text. It’s novelty lies in its ability to correct complete sentences that may contain multiple and interacting errors.
The invention comprises a decoder that performs a beam search over possible hypotheses (i.e., corrected versions of the sentence) to find the best possible correction for an input sentence. The search starts from the original error sentence. At each step, a set of proposers generates new hypotheses by making incremental changes to the current hypothesis. A set of experts scores these hypotheses on criteria of grammatical correctness. These experts include discriminative classifiers for specific error types, such as article and preposition errors. The final score for a hypothesis is a linear combination of the expert scores according to the decoder model. The weights of the decoder model are trained on a development set of error-annotated sentences.
Technology Readiness Level 4 on the scale by the Ministry of Defence Singapore.
About the Research Group
Dr. Hwee Tou Ng is a Professor of Computer Science at the National University of Singapore (NUS) and a Senior Faculty Member at the NUS Graduate School for Integrative Sciences and Engineering. His research focuses on natural language processing and information retrieval. He is a Fellow of the Association for Computational Linguistics (ACL) and a member of the China-Singapore Institute of Digital Media.