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

Kai Sheng Tai, Richard Socher, Christopher D. Manning
2/28/2015
cs.CLcs.AIcs.LG

Official code: stanfordnlp/treelstm (892 stars, GPL-2.0, last commit 2017-07-30).

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).

View on arXivView PDF

Code Implementations(1)

stanfordnlp/treelstmOfficial100%
GPL-2.0

Tree-structured Long Short-Term Memory networks (http://arxiv.org/abs/1503.00075)

892232Lua, JavaApr 2, 20159 years agoGPL-2.0

Similar Papers

Extending Memory for Language Modelling

83% match2023

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

83% match1 repo4.6k2018

Structured Sequence Modeling with Graph Convolutional Recurrent Networks

83% match1 repo1812016

Bayesian Networks for Named Entity Prediction in Programming Community Question Answering

83% match2023

The Lifted Matrix-Space Model for Semantic Composition

83% match2 repos1082017

Ordered Memory Baselines

83% match2023

Cite this paper

@article{tai2015improved,
  title  = {Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks},
  author = {Kai Sheng Tai and Richard Socher and Christopher D. Manning},
  year   = {2015},
  eprint = {1503.00075},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1503.00075}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1503.00075.svg)](https://codeofpaper.com/paper/1503.00075)

Discussion