Semantic Similarity Computing Model Based on Multi Model Fine-Grained Nonlinear Fusion

TL;DR

This paper introduces a multi-model nonlinear fusion approach combining statistical and deep learning methods to improve sentence similarity measurement in NLP, achieving 84% matching accuracy.

Contribution

It proposes a novel fusion model integrating multiple similarity measures with neural networks for better global sentence understanding.

Findings

Sentence similarity matching accuracy is 84%

F1 score of the model is 75%

Reduces feature granularity for global understanding

Abstract

Natural language processing (NLP) task has achieved excellent performance in many fields, including semantic understanding, automatic summarization, image recognition and so on. However, most of the neural network models for NLP extract the text in a fine-grained way, which is not conducive to grasp the meaning of the text from a global perspective. To alleviate the problem, the combination of the traditional statistical method and deep learning model as well as a novel model based on multi model nonlinear fusion are proposed in this paper. The model uses the Jaccard coefficient based on part of speech, Term Frequency-Inverse Document Frequency (TF-IDF) and word2vec-CNN algorithm to measure the similarity of sentences respectively. According to the calculation accuracy of each model, the normalized weight coefficient is obtained and the calculation results are compared. The weighted vector is input into the fully connected neural network to give the final classification results. As a result, the statistical sentence similarity evaluation algorithm reduces the granularity of feature extraction, so it can grasp the sentence features globally. Experimental results show that the matching of sentence similarity calculation method based on multi model nonlinear fusion is 84%, and the F1 value of the model is 75%.