Semantic error checking in automatic proofreading for Chinese texts

Semantic error checking is a weak point of automatic proofreading for Chinese texts, with few mature methods at present. The paper discusses the technology of semantic error detection for Chinese texts, proposes a strategy combining statistical and rules approaches, and uses the collocation relationship based on instances, statistics and rules to check errors. The strategy checks both local semantic restraints and remote semantic collocations, and achieves satisfactory results.