Unsupervised Learning of Explainable Parse Trees for Improved Generalisation
This work addresses the need for more explainable and semantically meaningful parse trees in natural language processing, offering incremental improvements over existing recursive neural network approaches.
The paper tackled the problem of recursive neural networks failing to learn meaningful grammar and semantics in parse trees by proposing an attention mechanism over Tree-LSTMs, resulting in improved performance on natural language inference, semantic relatedness, and sentiment analysis tasks compared to state-of-the-art methods.
Recursive neural networks (RvNN) have been shown useful for learning sentence representations and helped achieve competitive performance on several natural language inference tasks. However, recent RvNN-based models fail to learn simple grammar and meaningful semantics in their intermediate tree representation. In this work, we propose an attention mechanism over Tree-LSTMs to learn more meaningful and explainable parse tree structures. We also demonstrate the superior performance of our proposed model on natural language inference, semantic relatedness, and sentiment analysis tasks and compare them with other state-of-the-art RvNN based methods. Further, we present a detailed qualitative and quantitative analysis of the learned parse trees and show that the discovered linguistic structures are more explainable, semantically meaningful, and grammatically correct than recent approaches. The source code of the paper is available at https://github.com/atul04/Explainable-Latent-Structures-Using-Attention.