Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

TL;DR

This paper introduces Tree-LSTM, a novel extension of traditional LSTMs designed for tree-structured data, which significantly improves semantic representation and performance on language understanding tasks.

Contribution

The paper presents the Tree-LSTM, a new model that generalizes LSTMs to tree structures, capturing syntactic properties of language more effectively.

Findings

Tree-LSTM outperforms existing models on semantic relatedness prediction.

Tree-LSTM achieves state-of-the-art results on sentiment classification.

Tree-LSTM demonstrates superior ability to model hierarchical language structures.

Abstract

Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of sequence modeling tasks. The only underlying LSTM structure that has been explored so far is a linear chain. However, natural language exhibits syntactic properties that would naturally combine words to phrases. We introduce the Tree-LSTM, a generalization of LSTMs to tree-structured network topologies. Tree-LSTMs outperform all existing systems and strong LSTM baselines on two tasks: predicting the semantic relatedness of two sentences (SemEval 2014, Task 1) and sentiment classification (Stanford Sentiment Treebank).