Sentence with polysemous words can easily be interpreted as different meanings by different people even in a specific context, which will significantly reduce the quality of requirements documents.However, existing ambiguity detection mainly considers the sentence structure and cannot solve this problem well.In this paper, we consider sentence semantics and perform sentence ambiguity detection by introducing external semantic knowledge to explicitly modeling the different semantics of polysemy.Specifically, we determine the target polysemy in the given sentence according to the ambiguous vocabulary list.Furthermore, based on the fusion strategy we designed, we model the different semantics of polysemous word by introducing external semantic knowledge and predict the possible semantics of the sentence by measuring the the gap between different semantic fusion results and the original sentence.This is also the first work to introduce external semantic knowledge into ambiguity detection.The experimental results illustrate that our accuracy is higher than the baseline accuracy of ambiguity in existing research.

Pronoun anaphora ambiguity is very common in natural language descriptions, especially in specilized fileds such as computing, medicine and aerospace.When multiple antecedents appear before a pronoun word, readers with different background knowledge often have completely different understandings on a same word.In order to reduce such misunderstandings caused by ambiguity in the process of document propogation, we usually use manual methods to check the ambiguity of reference, which however cannot meet the increasing needs of detection with the development of various disciplines.In this paper, we propose a method to intelligently detect sentences with anaphora ambiguity.First of all, we identify criteria for ambiguous sentences and then use word embeddings to further detect ambiguity.Specifically, we propose a pronoun substitution strategy based on coreference resolution, and combine this strategy with word embedding techniques to generate a cross-domain anaphora ambiguity detection method.Finally, we carry out experiments on aerospace documents, which verify the effectiveness of our proposed method in anaphora ambiguity detection.