Hybridization between Neural Computing and Nature-Inspired Algorithms for a Sentence Similarity Model Based on the Attention Mechanism

Abstract

Sentence similarity analysis has been applied in many fields, such as machine translation, the question answering system, and voice customer service. As a basic task of natural language processing, sentence similarity analysis plays an important role in many fields. The task of sentence similarity analysis is to establish a sentence similarity scoring model through multi-features. In previous work, researchers proposed a variety of models to deal with the calculation of sentence similarity. But these models do not consider the association information of sentence pairs, but only input sentence pairs into the model. In this article, we propose a sentence feature extraction model based on multi-feature attention. In addition, with the development of deep learning and the application of nature-inspired algorithms, researchers have proposed various hybrid algorithms that combine nature-inspired algorithms with neural networks. The hybrid algorithms not only solve the problem of decision-making based on multiple features but also improve the performance of the model. In the model, we use the attention mechanism to extract sentence features and assign weight. Then, the convolutional neural network is used to reduce the dimension of the matrix. In the training process, we integrate the firefly algorithm in the neural networks. The experimental results show that the accuracy of our model is 74.21%.

A Web Knowledge-Driven Multimodal Retrieval Method in Computational Social Systems: Unsupervised and Robust Graph Convolutional Hashing

“…To value the intrinsic structural representation of features, with the aid of the Hadamard matric, Latent Structure Discrete Hashing Factorization (LSDHF) [27] decomposes similar structures in an unsupervised manner to further strengthen modality associations. However, this kind of shallow structure method is difficult to fully explore the semantic information of modality data through an independent manual feature encoding process [28], which reduces the effectiveness of hash encoding [13], [19].…”

“…Its main purpose is to use knowledge-driven computers to model, compute, and analyze social (web) data. Many researchers are also working to discover the social phenomena hidden in the increasingly complex large-scale social data, such as social network analysis [8], COVID-19 analysis [9], public opinion analysis [10], sentiment analysis [11], social media content analysis [12], similarity analysis [13], etc. They analyze social behaviors on multiple dimensions and levels to promote the further development of CSS.…”

“…1, since the modality data in different feature spaces have separate distribution structures, they fail to be directly compared. Therefore, we ought to map them to the same common subspace for similarity comparison while preserving the original semantic similarity [13]. In the scenario of enormous social datasets, low storage and real-time retrieval have brought tremendous challenges [15], [16].…”

Construction of English Translation Model Based on Neural Network Fuzzy Semantic Optimal Control

“…Under the situation of economic globalization and integration, economic, trade, and cultural exchanges are rapidly increasing, and the research on Chinese-French neural machine translation can help to further strengthen the exchanges between the two countries. However, since English has incomplete equivalence in lexical and syntactic aspects, no matching, and variation in verb tense and person, such incomplete equivalence undoubtedly brings greater difficulties and challenges to neural machine translation [ 3 ]. For English translation tasks, they can be classified into different levels according to different categorization methods.…”