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

Zhang, Peiying; Huang, Xingzhe; Wang, Yaqi; Jiang, Chunxiao; He, Simai; Wang, Haifeng

doi:10.1109/access.2021.3049378

Cited by 25 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within the semantic similarity approaches, as for instance the one recently presented in [47] for Neural Networks, or hybrid similarity measures combining the shortest path lengths and the depths of subsumers [30], below we restrict our attention to the methods based on the information content [14], [33], Formal Concept Analysis [13], [43], IFCA (Formal Concept Analysis with Interval Type-2 Fuzzy sets) [15], Geographical Information Systems [16], [40], and different application domains, such as health [1], [24], and network security [44], just to mention a few examples. However the IC approach, although recognized as "the state of the art on semantic similarity" [3], [8], has shown some limitations, as discussed below.…”

Section: Related Workmentioning

confidence: 99%

An Enriched Information-Theoretic Definition of Semantic Similarity in a Taxonomy

Formica

Taglino

2021

IEEE Access

View full text Add to dashboard Cite

This paper addresses the notion of semantic similarity between concepts organized according to a taxonomy, based on the well-known information content approach. This approach has been widely experimented in the literature over the years and, in general, outperforms other proposals which do not originate from it. However, it shows some limitations related to the notion of generic sense of a concept. In this paper we illustrate the problem arising by using the traditional approach, and a novel informationtheoretic definition of semantic similarity in a taxonomy is proposed which also takes into account the intended sense of a concept in a given context. This proposal has been applied to some among the most representative state-of-the-art similarity measures based on the information content approach, and the experiment shows that it achieves very high correlation values with human judgment.

show abstract

Section: Related Workmentioning

confidence: 99%

An Enriched Information-Theoretic Definition of Semantic Similarity in a Taxonomy

Formica

Taglino

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Ranasinghe et al used various combinations of GRU, Bi-LSTM, etc., in Siamese network structures to compare the representational power of various variants of the structure for text semantics [12]. Zhang et al combined TF-IDF and Jaccard coefcients with CNN to improve the representation of vectors for sentence features, but lacked semantic links between diferent words [13]. Guo et al analyzed the multiple semantic compositions of texts in terms of their frame structure and combined with the self-attention mechanism to enhance the representation of vectors for multiple semantic sentences, but lacked the representation of semantic relations between diferent texts [14].…”

Section: Introductionmentioning

confidence: 99%

Siamese Interaction and Fine-Tuning Representation of Chinese Semantic Matching Algorithm Based on RoBERTa-wwm-ext

Qiang

Wang³

et al. 2023

Mobile Information Systems

View full text Add to dashboard Cite

Semantic matching research is the cornerstone of research in the fields of natural language similarity measurement and sensor ontology matching (OM). In the existing Chinese semantic matching methods, there are some shortcomings, such as the single dimension of semantic expression, the insufficient expression of context semantic relations, and the insufficient interaction of semantic information between different sentences. This paper proposes a Chinese semantic matching algorithm based on RoBERTa-wwm-ext with Siamese interaction and fine-tuning representation (RSIFR). The RSIFR model initializes the model with RoBERTa-wwm-ext as a vector of text. Firstly, a Siamese structure with embedded soft alignment attention mechanism and BiLSTM is constructed to realize the information interaction between two sentences. Secondly, LSTM-BiLSTM network structure is constructed to enhance the expression of semantic logic before and after sentences. Then, build a training model with fine-tuning mechanism. Fine tune the text’s eigenvector parameters through label supervision. Finally, the fusion vectors of the sentence pairs are inserted into the MLP network layer, resulting in semantic matching results. RSIFR model starts from a variety of dimensions, strengthens the expression ability of vectors to text semantic relations, deeply mines the semantic similarities and differences between different sentences, and generally improves the Chinese semantic matching performance. Experiments on the public dataset LCQMC show that our model outperforms existing Chinese semantic matching models.

show abstract

“…Traditional sentence matching methods are mainly based on statistical characteristics of sentences ( Zhang et al (2021) ) or on word embedding ( Shen et al (2018) ) to directly calculate the similarity between sentences. But they often ignore the semantic features of sentences, which are not effective in complex situations.…”

Section: Introductionmentioning

confidence: 99%

MGMSN: Multi-Granularity Matching Model Based on Siamese Neural Network

Wang

Yang

2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

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

Cited by 25 publications

References 35 publications

An Enriched Information-Theoretic Definition of Semantic Similarity in a Taxonomy

An Enriched Information-Theoretic Definition of Semantic Similarity in a Taxonomy

Siamese Interaction and Fine-Tuning Representation of Chinese Semantic Matching Algorithm Based on RoBERTa-wwm-ext

MGMSN: Multi-Granularity Matching Model Based on Siamese Neural Network

Contact Info

Product

Resources

About