A Deep Fusion Matching Network Semantic Reasoning Model
Open Access
- 27 March 2022
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 12 (7) , 3416
Abstract
As the vital technology of natural language understanding, sentence representation reasoning technology mainly focuses on sentence representation methods and reasoning models. Although the performance has been improved, there are still some problems, such as incomplete sentence semantic expression, lack of depth of reasoning model, and lack of interpretability of the reasoning process. Given the reasoning model’s lack of reasoning depth and interpretability, a deep fusion matching network is designed in this paper, which mainly includes a coding layer, matching layer, dependency convolution layer, information aggregation layer, and inference prediction layer. Based on a deep matching network, the matching layer is improved. Furthermore, the heuristic matching algorithm replaces the bidirectional long-short memory neural network to simplify the interactive fusion. As a result, it improves the reasoning depth and reduces the complexity of the model; the dependency convolution layer uses the tree-type convolution network to extract the sentence structure information along with the sentence dependency tree structure, which improves the interpretability of the reasoning process. Finally, the performance of the model is verified on several datasets. The results show that the reasoning effect of the model is better than that of the shallow reasoning model, and the accuracy rate on the SNLI test set reaches 89.0%. At the same time, the semantic correlation analysis results show that the dependency convolution layer is beneficial in improving the interpretability of the reasoning process.Keywords
Funding Information
- Sichuan Science and Technology Program (2021YFQ0003)
This publication has 28 references indexed in Scilit:
- A label-oriented loss function for learning sentence representationsComputer Speech & Language, 2021
- Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text ClassificationIEEE Transactions on Knowledge and Data Engineering, 2019
- Classifying Promoters by Interpreting the Hidden Information of DNA Sequences via Deep Learning and Combination of Continuous FastText N-GramsFrontiers in Bioengineering and Biotechnology, 2019
- Semantic representation for visual reasoningMATEC Web of Conferences, 2019
- A Word Elimination Strategy for Learning Document RepresentationIOP Conference Series: Materials Science and Engineering, 2018
- Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification2018
- Improved Adam Optimizer for Deep Neural Networks2018
- Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot TranslationTransactions of the Association for Computational Linguistics, 2017
- Enhanced LSTM for Natural Language Inference2017
- Hybrid computing using a neural network with dynamic external memoryNature, 2016