The words in the sentence are related each other by syntax and semantic. The cooccurrence of similar words between sentence has the mutual inspire contribution to the similarity.
句子中出现的词汇之间有着各种各样的语法、语义联系,对于相似度计算,相似词对的共现是有着激励效应的。
参考来源 - 基于《知网》的句子相似度计算的研究·2,447,543篇论文数据，部分数据来源于NoteExpress
为了提取简洁的形式背景，提出了相似词集集合的概念以改进单一词汇所带来的冗余。
To extract a concise formal context, the set of similar word set was proposed to reduce the redundancy caused by a single word.
本文利用三元模型，通过引入相似词，采取“词形-相似词-词性”三步回退的策略，比较好地缓解了数据稀疏问题。
Based on trigram models, this paper proposes a three-step method of "word-similar word-part of speech" by incorporating the similar words and solves the problem of sparse data to a large extent.
许多语言，譬如法语和意大利语，都有相似的词。
There is a similar word in many languages, for example in French and Italian.
应用推荐