A Hybrid Model for Chinese Spelling Check

Abstract

Spelling check for Chinese has more challenging difficulties than that for other languages. A hybrid model for Chinese spelling check is presented in this article. The hybrid model consists of three components: one graph-based model for generic errors and two independently trained models for specific errors. In the graph model, a directed acyclic graph is generated for each sentence, and the single-source shortest-path algorithm is performed on the graph to detect and correct general spelling errors at the same time. Prior to that, two types of errors over functional words (characters) are first solved by conditional random fields: the confusion of “在” ( at ) (pinyin is zai in Chinese), “再” ( again , more , then ) (pinyin: zai ) and “的” ( of ) (pinyin: de ), “地” (- ly , adverb-forming particle) (pinyin: de ), and “得” ( so that , have to ) (pinyin: de ). Finally, a rule-based model is exploited to distinguish pronoun usage confusion: “她” ( she ) (pinyin: ta ), “他” ( he ) (pinyin: ta ), and some other common collocation errors. The proposed model is evaluated on the standard datasets released by the SIGHAN Bake-off shared tasks, giving state-of-the-art results.

FASPell: A Fast, Adaptable, Simple, Powerful Chinese Spell Checker Based On DAE-Decoder Paradigm

“…Thus, FASPell is faster than their model. Zhao et al (2017) filter candidates by finding the single-source shortest path (SSSP) in a directed graph consisting of all candidates for every token in a sentence. The algorithm they used has a time complexity of O(|V | + |E|) where |V | is the number of vertices and |E| is the number of edges in the graph (Eppstein, 1998).…”

Chunk-based Chinese Spelling Check with Global Optimization

“…For the candidate selection phase, the perplexity from language models is frequently used for selecting the most reasonable candidate (Chang, 1995;Jia et al, 2013;Yu and Li, 2014;Yeh et al, 2015). Rules are effective and often included in the CSC model for handling singlecharacter errors (Hsieh et al, 2015;Zhang et al, 2015;Zhao et al, 2017). Recent researchers rely on supervised methods to achieve further improvement.…”

“…Yeh et al (2015) employ a maximum entropy (ME) model for correction selection. Zhao et al (2017) use conditional random fields (CRFs) to handle two types of misspelled single-character word. Cheng et al (2020) propose to incorporate phonological and visual similarity knowledge into the CSC models via a graph convolutional network.…”

“…In order to explore and utilize the word-level information, the word-based methods are designed to do word segmentation and spelling error corrections jointly. Previous works show that the wordbased correction models often perform better than their character-based counterparts (Jia et al, 2013;Hsieh et al, 2015;Yeh et al, 2015;Zhao et al, 2017). Since word-based correction models usually apply a pipeline of submodules and handle special cases (e.g., single-character words) individually, the complex architecture makes it difficult to perform global optimization.…”

SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings

“…However, our concerned task, hypernym discovery, is rather more challenging since it requires the systems to explore the semantic connection with all the exhausted candidates in the latent space and rank a candidate set instead of a binary classification in previous work. Recently, neural network (NN) models have shown competitive or even better results than traditional linear models with handcrafted sparse fea-tures (Qin et al, 2016b;?,a;Wang et al, 2016c;Zhao et al, 2017a;Wang et al, 2017;Qin et al, 2017;Zhao et al, 2017b;Li et al, 2018). In this work, we introduce a neural network architecture for the concerned task and empirically study various neural networks to model the distributed representations for words and phrases.…”