Neural Tree Indexers for Text Understanding

TL;DR

Neural Tree Indexers (NTI) are a novel, syntax-independent tree-structured model that effectively combines the advantages of RNNs and recursive models, achieving state-of-the-art results in multiple NLP tasks.

Contribution

Introduces NTI, a robust, syntax-independent tree-structured neural model that processes text in a bottom-up manner with attention, bridging the gap between RNNs and recursive models.

Findings

Achieved state-of-the-art performance on NLP tasks

Outperformed existing recurrent and recursive neural networks

Validated effectiveness across multiple NLP applications

Abstract

Recurrent neural networks (RNNs) process input text sequentially and model the conditional transition between word tokens. In contrast, the advantages of recursive networks include that they explicitly model the compositionality and the recursive structure of natural language. However, the current recursive architecture is limited by its dependence on syntactic tree. In this paper, we introduce a robust syntactic parsing-independent tree structured model, Neural Tree Indexers (NTI) that provides a middle ground between the sequential RNNs and the syntactic treebased recursive models. NTI constructs a full n-ary tree by processing the input text with its node function in a bottom-up fashion. Attention mechanism can then be applied to both structure and node function. We implemented and evaluated a binarytree model of NTI, showing the model achieved the state-of-the-art performance on three different NLP tasks: natural language inference, answer sentence selection, and sentence classification, outperforming state-of-the-art recurrent and recursive neural networks.