Neural Tree Indexers for Text Understanding

EACL 2017  ·  Tsendsuren Munkhdalai, Hong Yu ·

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.

PDF Abstract EACL 2017 PDF EACL 2017 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Natural Language Inference SNLI 300D Full tree matching NTI-SLSTM-LSTM w/ global attention % Test Accuracy 87.3 # 44
% Train Accuracy 88.5 # 56
Parameters 3.2m # 4
Natural Language Inference SNLI 300D NTI-SLSTM-LSTM encoders % Test Accuracy 83.4 # 82
% Train Accuracy 82.5 # 74
Parameters 4.0m # 4

Methods


No methods listed for this paper. Add relevant methods here