arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0804.0143cs.CL
收藏

高阶同现对词汇语义相似度的影响

Effects of High-Order Co-occurrences on Word Semantic Similarities

Laboratoire Leibniz-IMAG(莱布尼茨-IMAG实验室);CNRS(法国国家科学研究中心);L.P.C(语言与沟通实验室);Université de Provence(普罗旺斯大学)

Benoît Lemaire, Guy Denhière

摘要:

建立了一个通过文本构建词义的计算模型,内置的逐段模拟共现值对词义相似度的影响。语义相似性在这里被视为关联。结果表明,两个词W1和W2之间的相似性随着同现而强烈增加,随着W1没有W2或W2没有W1的出现而降低,并且随着高阶同现而略微增加。因此,将相似性操作化为共现频率可能会引入偏差:首先,有些情况下存在相似性而没有共现,其次,共现频率高估了相似性。

英文摘要:

A computational model of the construction of word meaning through exposure to texts is built in order to simulate the effects of co-occurrence values on word semantic similarities, paragraph by paragraph. Semantic similarity is here viewed as association. It turns out that the similarity between two words W1 and W2 strongly increases with a co-occurrence, decreases with the occurrence of W1 without W2 or W2 without W1, and slightly increases with high-order co-occurrences. Therefore, operationalizing similarity as a frequency of co-occurrence probably introduces a bias: first, there are cases in which there is similarity without co-occurrence and, second, the frequency of co-occurrence overestimates similarity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑