Matching Text with Deep Mutual Information Estimation
This work addresses text matching, a core NLP problem, by improving representation learning, though it appears incremental as it builds on existing neural methods with mutual information integration.
The paper tackled the challenge of retaining content and structure information in text matching by introducing TIM, a neural approach that incorporates deep mutual information estimation, which achieved better experimental results on tasks like natural language inference and paraphrase identification without using external pretraining data.
Text matching is a core natural language processing research problem. How to retain sufficient information on both content and structure information is one important challenge. In this paper, we present a neural approach for general-purpose text matching with deep mutual information estimation incorporated. Our approach, Text matching with Deep Info Max (TIM), is integrated with a procedure of unsupervised learning of representations by maximizing the mutual information between text matching neural network's input and output. We use both global and local mutual information to learn text representations. We evaluate our text matching approach on several tasks including natural language inference, paraphrase identification, and answer selection. Compared to the state-of-the-art approaches, the experiments show that our method integrated with mutual information estimation learns better text representation and achieves better experimental results of text matching tasks without exploiting pretraining on external data.