Corpus and unsupervised benchmark: Towards Tagalog grammatical error correction

Abstract

Grammatical error correction (GEC) is a challenging task for natural language processing techniques. Many efforts to address GEC have been made for high-resource languages such as English or Chinese. However, limited work has been done for low-resource languages because of the lack of large annotated corpora. In low-resource languages, the current unsupervised GEC based on language model scoring performs well. However, the pre-trained language model is still to be explored in this context. This study proposes a BERT-based unsupervised GEC framework that primarily addresses word-level errors, where GEC is viewed as a multi-class classification task. The framework contains three modules: a data flow construction module, a sentence perplexity scoring module, and an error detecting and correcting module. We propose a novel scoring method for pseudo-perplexity to evaluate a sentence’s probable correctness and construct a Tagalog corpus for Tagalog GEC research. It obtains competitive performance on the self-constructed Tagalog corpus and the open-source Indonesian corpus, and it demonstrates that our framework is complementary to the baseline methods for low-resource GEC tasks. Our corpus can be obtained from https://github.com/GKLMIP/TagalogGEC.