TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Improved Semantic Representations From Tree-Structured Lon...

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

Kai Sheng Tai, Richard Socher, Christopher D. Manning

2015-02-28IJCNLP 2015 7Sentiment AnalysisSemantic SimilaritySentiment ClassificationGeneral Classification
PaperPDFCodeCodeCodeCodeCodeCodeCodeCodeCodeCode(official)CodeCodeCodeCodeCodeCode

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).

Results

TaskDatasetMetricValueModel
Language ModellingSICKMSE0.2532Dependency Tree-LSTM (Tai et al., 2015)
Language ModellingSICKPearson Correlation0.8676Dependency Tree-LSTM (Tai et al., 2015)
Language ModellingSICKSpearman Correlation0.8083Dependency Tree-LSTM (Tai et al., 2015)
Language ModellingSICKMSE0.2736Bidirectional LSTM (Tai et al., 2015)
Language ModellingSICKPearson Correlation0.8567Bidirectional LSTM (Tai et al., 2015)
Language ModellingSICKSpearman Correlation0.7966Bidirectional LSTM (Tai et al., 2015)
Language ModellingSICKMSE0.2831LSTM (Tai et al., 2015)
Language ModellingSICKPearson Correlation0.8528LSTM (Tai et al., 2015)
Language ModellingSICKSpearman Correlation0.7911LSTM (Tai et al., 2015)
Sentiment AnalysisSST-5 Fine-grained classificationAccuracy51Constituency Tree-LSTM
Sentiment AnalysisSST-2 Binary classificationAccuracy88Consistency Tree LSTM with tuned Glove vectors [tai2015improved]
Sentiment AnalysisSST-2 Binary classificationAccuracy86.32-layer LSTM [tai2015improved]
Sentence Pair ModelingSICKMSE0.2532Dependency Tree-LSTM (Tai et al., 2015)
Sentence Pair ModelingSICKPearson Correlation0.8676Dependency Tree-LSTM (Tai et al., 2015)
Sentence Pair ModelingSICKSpearman Correlation0.8083Dependency Tree-LSTM (Tai et al., 2015)
Sentence Pair ModelingSICKMSE0.2736Bidirectional LSTM (Tai et al., 2015)
Sentence Pair ModelingSICKPearson Correlation0.8567Bidirectional LSTM (Tai et al., 2015)
Sentence Pair ModelingSICKSpearman Correlation0.7966Bidirectional LSTM (Tai et al., 2015)
Sentence Pair ModelingSICKMSE0.2831LSTM (Tai et al., 2015)
Sentence Pair ModelingSICKPearson Correlation0.8528LSTM (Tai et al., 2015)
Sentence Pair ModelingSICKSpearman Correlation0.7911LSTM (Tai et al., 2015)
Semantic SimilaritySICKMSE0.2532Dependency Tree-LSTM (Tai et al., 2015)
Semantic SimilaritySICKPearson Correlation0.8676Dependency Tree-LSTM (Tai et al., 2015)
Semantic SimilaritySICKSpearman Correlation0.8083Dependency Tree-LSTM (Tai et al., 2015)
Semantic SimilaritySICKMSE0.2736Bidirectional LSTM (Tai et al., 2015)
Semantic SimilaritySICKPearson Correlation0.8567Bidirectional LSTM (Tai et al., 2015)
Semantic SimilaritySICKSpearman Correlation0.7966Bidirectional LSTM (Tai et al., 2015)
Semantic SimilaritySICKMSE0.2831LSTM (Tai et al., 2015)
Semantic SimilaritySICKPearson Correlation0.8528LSTM (Tai et al., 2015)
Semantic SimilaritySICKSpearman Correlation0.7911LSTM (Tai et al., 2015)

Related Papers

AdaptiSent: Context-Aware Adaptive Attention for Multimodal Aspect-Based Sentiment Analysis2025-07-17SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts2025-07-17AI Wizards at CheckThat! 2025: Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles2025-07-15DCR: Quantifying Data Contamination in LLMs Evaluation2025-07-15SentiDrop: A Multi Modal Machine Learning model for Predicting Dropout in Distance Learning2025-07-14GNN-CNN: An Efficient Hybrid Model of Convolutional and Graph Neural Networks for Text Representation2025-07-10SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression2025-07-08FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection2025-07-06