DEIM: An effective deep encoding and interaction model for sentence matching

20 Mar 2022  ·  Kexin Jiang, Yahui Zhao, Rongyi Cui, Zhenguo Zhang ·

Natural language sentence matching is the task of comparing two sentences and identifying the relationship between them.It has a wide range of applications in natural language processing tasks such as reading comprehension, question and answer systems. The main approach is to compute the interaction between text representations and sentence pairs through an attention mechanism, which can extract the semantic information between sentence pairs well. However,this kind of method can not gain satisfactory results when dealing with complex semantic features. To solve this problem, we propose a sentence matching method based on deep encoding and interaction to extract deep semantic information. In the encoder layer,we refer to the information of another sentence in the process of encoding a single sentence, and later use a heuristic algorithm to fuse the information. In the interaction layer, we use a bidirectional attention mechanism and a self-attention mechanism to obtain deep semantic information.Finally, we perform a pooling operation and input it to the MLP for classification. we evaluate our model on three tasks: recognizing textual entailment, paraphrase recognition, and answer selection. We conducted experiments on the SNLI and SciTail datasets for the recognizing textual entailment task, the Quora dataset for the paraphrase recognition task, and the WikiQA dataset for the answer selection task. The experimental results show that the proposed algorithm can effectively extract deep semantic features that verify the effectiveness of the algorithm on sentence matching tasks.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Natural Language Inference SNLI DEIM % Test Accuracy 88.9 # 22
% Train Accuracy 92.6 # 27
Parameters 22m # 4

Methods


No methods listed for this paper. Add relevant methods here