PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pages 5958–5967 August 1–6, 2021. ©2021 Association for Computational Linguistics 5958 PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check Li Huang1,2, Junjie Li2, Weiwei Jiang2, Zhiyu Zhang2, Minchuan Chen2, Shaojun Wang2 and Jing Xiao2 1Fudan University 2Ping An Technology lhuang9703@gmail.com, junjielee815@gmail.com Abstract Chinese Spelling Check (CSC) is a challeng- ing task due to the complex characteristics of Chinese characters. Statistics reveal that most Chinese spelling errors belong to phonological or visual errors. However, previous methods rarely utilize phonological and morphological knowledge of Chinese characters or heavily rely on external resources to model their sim- ilarities. To address the above issues, we pro- pose a novel end-to-end trainable model called PHMOSpell, which promotes the performance of CSC with multi-modal information. Specif- ically, we derive pinyin and glyph representa- tions for Chinese characters from audio and visual modalities respectively, which are inte- grated into a pre-trained language model by a well-designed adaptive gating mechanism. To verify its effectiveness, we conduct compre- hensive experiments and ablation tests. Ex- perimental results on three shared benchmarks demonstrate that our model consistently out- performs previous state-of-the-art models. 1 Introduction Chinese Spelling Check (CSC) is a fundamen- tal task in Chinese Natural Language Processing (NLP), which aims to automatically detect and cor- rect spelling errors in Chinese sentences. These errors typically consist of human writing errors and machine recognition errors by automatic speech recognition (ASR) or optical character recognition (OCR) systems (Yu et al., 2014). CSC serves as a preliminary component for other downstream tasks like information retrieval (IR) in search engine, thus significantly affects the final performance of these tasks. Chinese is an ideograph language which contains numerous characters and has no between-word de- limiters. These characteristics make its spelling check more difficult than other alphabetical lan- guages such as English. Specifically, for error p-s error: wrong sentence: 人们必(pinyin: bi4) 生去追求的目标。 ground truth: 人们毕(pinyin: bi4) 生去追求的目标。 v-s error: wrong sentence: 迎接每一个固(radicals: 古,口) 难。 ground truth: 迎接每一个困(radicals: 木,口) 难。 Table 1: Examples of p-s (phonological similarity) er- ror and v-s (visual similarity) error from SIGHAN13 (Wu et al., 2013). Here, the ground truth of the p-s error means “The goal that people pursue throughout their lives” and the ground truth of the v-s error means “Get prepared for every difficulty”. detection, Chinese words usually consist of sev- eral characters and have no clear word boundaries, which makes it impossible to detect spelling errors just using individual word or character. They must be put in a specific sentence to capture contextual semantic information. For error correction, how to select correct candidates from tremendous char- acter sets remains a great challenge. In contrast to English words that are composed of a small set of alphabet letters, there are more than 10k Chi- nese characters, and 3.5k of them are frequently used (Wang et al., 2019b). Besides, unlike English, almost all Chinese spelling errors are real-word errors …

Content truncated to 500 words