Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
Kai Sheng Tai, Richard Socher, Christopher D. Manning
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/stanfordnlp/treelstmOfficialIn papertorch★ 0
- github.com/rohitguptacs/ReValtorch★ 0
- github.com/tensorflow/foldtf★ 0
- github.com/Mind23-2/MindCode-17mindspore★ 0
- github.com/jayanti-prasad/TreeLSTMpytorch★ 0
- github.com/zxk19981227/LSTM-SSTpytorch★ 0
- github.com/munashe5/SemanticTreeLSTMtf★ 0
- github.com/dmlc/dgl/tree/master/examples/pytorch/tree_lstmpytorch★ 0
- github.com/EmilReinert/DeepLearningPipelinespytorch★ 0
- github.com/vastsak/tree_structured_grutf★ 0
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).
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| SICK | Dependency Tree-LSTM (Tai et al., 2015) | MSE | 0.25 | — | Unverified |
| SICK | Bidirectional LSTM (Tai et al., 2015) | MSE | 0.27 | — | Unverified |
| SICK | LSTM (Tai et al., 2015) | MSE | 0.28 | — | Unverified |