mlsanityData to 7 Oct 2026

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

arXiv 1503.00075 ↗First posted 28 Feb 2015cs.CL cs.AI cs.LGcited by 305

Not on the map. Why?

Abstract (arXiv)

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).

Key facts. Cited by 305 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 108; 2022: 66; 2023: 56; 2024: 27; 2025: 32; 2026: 16.

305 papers.

Sort:

By area:

  1. 2021A Survey on Automated Fact-Checkingcited by 376
  2. 2021TransVG: End-to-End Visual Grounding with Transformerscited by 269
  3. 2022Learning on Large-scale Text-attributed Graphs via Variational Inferencecited by 153
  4. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  5. 2022A Survey of Deep Learning for Mathematical Reasoningcited by 124
  6. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 113
  7. 2021Directed Acyclic Graph Network for Conversational Emotion Recognitioncited by 97
  8. 2021A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learningcited by 82
  9. 2023SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networkscited by 82
  10. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  11. 2021Recovering the Unbiased Scene Graphs from the Biased Onescited by 71
  12. 2021Directed Acyclic Graph Neural Networkscited by 70
38 more
  1. 2024Repetition Improves Language Model Embeddingscited by 70
  2. 2021Language-Agnostic Representation Learning of Source Code from Structure and Contextcited by 63
  3. 2021SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representationcited by 63
  4. 2021A Review of Graph Neural Networks and Their Applications in Power Systemscited by 62
  5. 2022Testing Relational Understanding in Text-Guided Image Generationcited by 59
  6. 2021Fully Convolutional Scene Graph Generationcited by 57
  7. 2024A Survey on Deep Learning for Theorem Provingcited by 55
  8. 2023Grokking of Hierarchical Structure in Vanilla Transformerscited by 53
  9. 2021Adversarial Text-to-Image Synthesis: A Reviewcited by 52
  10. 2021Complex Knowledge Base Question Answering: A Surveycited by 52
  11. 2021Syntax-BERT: Improving Pre-trained Transformers with Syntax Treescited by 51
  12. 2021Look Before You Leap: Learning Landmark Features for One-Stage Visual Groundingcited by 51
  13. 2021Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualizationcited by 51
  14. 2024Towards a Foundation Model for Partial Differential Equations: Multi-Operator Learning and Extrapolationcited by 45
  15. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repaircited by 43
  16. 2022TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformercited by 41
  17. 2022Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scalecited by 40
  18. 2022Characterizing Intrinsic Compositionality in Transformers with Tree Projectionscited by 40
  19. 2023SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometrycited by 38
  20. 2022On the Explainability of Natural Language Processing Deep Modelscited by 37
  21. 2021Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Taskscited by 32
  22. 2021Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Informationcited by 31
  23. 2021Learning Algebraic Recombination for Compositional Generalizationcited by 31
  24. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  25. 2021Structured Sentiment Analysis as Dependency Graph Parsingcited by 28
  26. 2021Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Errorcited by 28
  27. 2023ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphscited by 27
  28. 2021Substructure Substitution: Structured Data Augmentation for NLPcited by 25
  29. 2021Segmentation-grounded Scene Graph Generationcited by 25
  30. 2021Curvature Graph Neural Networkcited by 24
  31. 2022Transformers over Directed Acyclic Graphscited by 23
  32. 2021End-to-end Semantic Role Labeling with Neural Transition-based Modelcited by 22
  33. 2022Knowledge Base Question Answering: A Semantic Parsing Perspectivecited by 22
  34. 2022Graph Neural Networks for Moleculescited by 21
  35. 2021Improving Code Summarization with Block-wise Abstract Syntax Tree Splittingcited by 19
  36. 2021R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modelingcited by 19
  37. 2021Multiplex Graph Neural Network for Extractive Text Summarizationcited by 19
  38. 2021ProTo: Program-Guided Transformer for Program-Guided Taskscited by 19

50 most cited of 305 All 305 (JSON)