TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Semantic Similarity	SICK	LSTM (Tai et al., 2015)	MSE	0.2831	# 4
Semantic Similarity	SICK	LSTM (Tai et al., 2015)	Pearson Correlation	0.8528	# 4
Semantic Similarity	SICK	LSTM (Tai et al., 2015)	Spearman Correlation	0.7911	# 4
Semantic Similarity	SICK	Bidirectional LSTM (Tai et al., 2015)	MSE	0.2736	# 3
Semantic Similarity	SICK	Bidirectional LSTM (Tai et al., 2015)	Pearson Correlation	0.8567	# 3
Semantic Similarity	SICK	Bidirectional LSTM (Tai et al., 2015)	Spearman Correlation	0.7966	# 2
Semantic Similarity	SICK	Dependency Tree-LSTM (Tai et al., 2015)	MSE	0.2532	# 1
Semantic Similarity	SICK	Dependency Tree-LSTM (Tai et al., 2015)	Pearson Correlation	0.8676	# 1
Semantic Similarity	SICK	Dependency Tree-LSTM (Tai et al., 2015)	Spearman Correlation	0.8083	# 1
Natural Language Inference	SNLI	CT-LSTM [[Tai et al.2015]]	% Test Accuracy	88.0	# 39
Natural Language Inference	SNLI	LSTM [[Tai et al.2015]]	% Test Accuracy	84.9	# 75
Natural Language Inference	SNLI	2-layer LSTM [[Tai et al.2015]]	% Test Accuracy	86.3	# 56
Sentiment Analysis	SST-2 Binary classification	2-layer LSTM[tai2015improved]	Accuracy	86.3	# 77
Sentiment Analysis	SST-2 Binary classification	CT-LSTM[tai2015improved]	Accuracy	88.0	# 68
Sentiment Analysis	SST-5 Fine-grained classification	Constituency Tree-LSTM	Accuracy	51.0	# 16

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/improved-semantic-representations-from-tree/semantic-similarity-on-sick)](https://paperswithcode.com/sota/semantic-similarity-on-sick?p=improved-semantic-representations-from-tree)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/improved-semantic-representations-from-tree/sentiment-analysis-on-sst-5-fine-grained)](https://paperswithcode.com/sota/sentiment-analysis-on-sst-5-fine-grained?p=improved-semantic-representations-from-tree)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/improved-semantic-representations-from-tree/natural-language-inference-on-snli)](https://paperswithcode.com/sota/natural-language-inference-on-snli?p=improved-semantic-representations-from-tree)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/improved-semantic-representations-from-tree/sentiment-analysis-on-sst-2-binary)](https://paperswithcode.com/sota/sentiment-analysis-on-sst-2-binary?p=improved-semantic-representations-from-tree)`

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

IJCNLP 2015 · Kai Sheng Tai, Richard Socher, Christopher D. Manning ·

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).

PDF Abstract IJCNLP 2015 PDF IJCNLP 2015 Abstract

Code

Add Remove Mark official

stanfordnlp/treelstm official

877

dmlc/dgl

12,977

dmlc/dgl

12,977

tensorflow/fold

1,821

dasguptar/treelstm.pytorch

547

See all 16 implementations

Tasks

Add Remove

General Classification

Semantic Similarity

Sentiment Analysis

Sentiment Classification

Datasets

SST SST-2

SNLI

SICK SST-5

Results from the Paper

Edit

Ranked #1 on Semantic Similarity on SICK

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Semantic Similarity	SICK	LSTM (Tai et al., 2015)	MSE	0.2831	# 4	Compare
			Pearson Correlation	0.8528	# 4	Compare
			Spearman Correlation	0.7911	# 4	Compare
Semantic Similarity	SICK	Bidirectional LSTM (Tai et al., 2015)	MSE	0.2736	# 3	Compare
			Pearson Correlation	0.8567	# 3	Compare
			Spearman Correlation	0.7966	# 2	Compare
Semantic Similarity	SICK	Dependency Tree-LSTM (Tai et al., 2015)	MSE	0.2532	# 1	Compare
			Pearson Correlation	0.8676	# 1	Compare
			Spearman Correlation	0.8083	# 1	Compare
Natural Language Inference	SNLI	CT-LSTM [[Tai et al.2015]]	% Test Accuracy	88.0	# 39	Compare
Natural Language Inference	SNLI	LSTM [[Tai et al.2015]]	% Test Accuracy	84.9	# 75	Compare
Natural Language Inference	SNLI	2-layer LSTM [[Tai et al.2015]]	% Test Accuracy	86.3	# 56	Compare
Sentiment Analysis	SST-2 Binary classification	2-layer LSTM[tai2015improved]	Accuracy	86.3	# 77	Compare
Sentiment Analysis	SST-2 Binary classification	CT-LSTM[tai2015improved]	Accuracy	88.0	# 68	Compare
Sentiment Analysis	SST-5 Fine-grained classification	Constituency Tree-LSTM	Accuracy	51.0	# 16	Compare

Methods

Add Remove

LSTM • Sigmoid Activation • Tanh Activation

Edit Social Preview

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

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove