基于SCDV及各向异性调整BERT的文本语义消歧方法

Solving the problem of ambiguity of text words is important for text representation, and it can accurately define the semantic characteristics of words in a specific context. Aiming at the polysemy and contextual characteristics of words, this paper proposed a semantic disambiguation model of SCDVAB. The main innovations are: Based on the partition average technology, it can convert scene corpus into document embedding, and introduce anisotropy to improve the sparse composite document vector (SCDV) algorithm of soft clustering to improve the contextual representation ability of BERT; and then it can improve the ability of text semantic disambiguation by embedding the BERT words after adjusting the anisotropy as a static word vector. Through many experiments, SCDVAB model is significantly better than the traditional text disambiguation algorithm. SCDVAB model can effectively improve the comprehensive performance of text semantic disambiguation.