MacBERT-based Multi-granularity Fusion Text Semantic Matching

Semantic matching is a core task in Chinese NLP, critical for applications like QA systems and recommendation engines. Existing methods often use uniform sentence modeling, overlooking multi-level semantic expressions. We propose a MacBERT-based multi-granularity fusion model that employs hybrid keyword-intent extraction and soft-alignment attention to integrate features at different semantic levels. Experiments on two Chinese short-text datasets show our model achieves significantly higher accuracy than baselines, demonstrating strong practical utility. (Abstract)

• Publication year

  2025

• Venue

  2025 International Conference on Signal Processing and Communication Technology (SPCT)

• Publication date

  2025-12-05

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/SPCT68223.2025.11406821
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Comparative Study on Embedding Models for Keyword Extraction Using KeyBERT Method

  2023cited by this paper
• Learning to Tokenize for Generative Retrieval

  2023cited by this paper
• MGMSN: Multi-Granularity Matching Model Based on Siamese Neural Network

  2022cited by this paper
• MatchACNN: A Multi-Granularity Deep Matching Model

  2022cited by this paper
• LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching

  2021cited by this paper
• Sentence pair modeling based on semantic feature map for human interaction with IoT devices

  2021cited by this paper
• On the Opportunities and Risks of Foundation Models

  2021cited by this paper
• A simple and efficient text matching model based on deep interaction

  2021cited by this paper
• Chinese Sentence Semantic Matching Based on Multi-Granularity Fusion Model

  2020cited by this paper
• Is Word Segmentation Necessary for Deep Learning of Chinese Representations?

  2019cited by this paper
• LCQMC:A Large-scale Chinese Question Matching Corpus

  2018cited by this paper
• The BQ Corpus: A Large-scale Domain-specific Chinese Corpus For Sentence Semantic Equivalence Identification

  2018cited by this paper
• Focal Loss for Dense Object Detection

  2017cited by this paper
• Multi-Granularity Neural Sentence Model for Measuring Short Text Similarity

  2017cited by this paper
• Character-level Convolutional Networks for Text Classification

  2015cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• SEMANTIC SIMILARITY MODELING BASED ON MULTI-GRANULARITY INTERACTION MATCHING

  year unknowncited by this paper

• No citing papers are available for this paper.