# Top-down Tree Long Short-Term Memory Networks

arXiv: https://arxiv.org/abs/1511.00060 · HTML: https://mlsanity.com/paper/1511.00060/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2015.

## Built on by (most cited first, 12 of 12)

- [Directed Acyclic Graph Neural Networks](https://mlsanity.com/paper/2101.07965/) (2021)
- [Algorithm Research of ELMo Word Embedding and Deep Learning Multimodal Transformer in Image Description](https://mlsanity.com/paper/2408.06357/) (2024)
- [Structured Code Representations Enable Data-Efficient Adaptation of Code Language Models](https://mlsanity.com/paper/2401.10716/) (2024)
- [Revisiting the Phenomenon of Syntactic Complexity Convergence on German Dialogue Data](https://mlsanity.com/paper/2408.12177/) (2024)
- [Learning Better Sentence Representation with Syntax Information](https://mlsanity.com/paper/2101.03343/) (2021)
- [Trees in transformers: a theoretical analysis of the Transformer's ability to represent trees](https://mlsanity.com/paper/2112.11913/) (2021)
- [Syntactic Inductive Biases for Deep Learning Methods](https://mlsanity.com/paper/2206.04806/) (2022)
- [Breaking BERT: Evaluating and Optimizing Sparsified Attention](https://mlsanity.com/paper/2210.03841/) (2022)
- [Trajectory Data Mining and Trip Travel Time Prediction on Specific Roads](https://mlsanity.com/paper/2407.07030/) (2024)
- [Recursive Function Definitions in Static Dataflow Graphs and their Implementation in TensorFlow](https://mlsanity.com/paper/2410.20225/) (2024)
- [A Long Short-Term Memory (LSTM) Model for Business Sentiment Analysis Based on Recurrent Neural Network](https://mlsanity.com/paper/2509.03060/) (2025)
- [Top-down string-to-dependency Neural Machine Translation](https://mlsanity.com/paper/2603.27938/) (2026)

## Abstract (arXiv)

Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have been successfully applied to a variety of sequence modeling tasks. In this paper we develop Tree Long Short-Term Memory (TreeLSTM), a neural network model based on LSTM, which is designed to predict a tree rather than a linear sequence. TreeLSTM defines the probability of a sentence by estimating the generation probability of its dependency tree. At each time step, a node is generated based on the representation of the generated sub-tree. We further enhance the modeling power of TreeLSTM by explicitly representing the correlations between left and right dependents. Application of our model to the MSR sentence completion challenge achieves results beyond the current state of the art. We also report results on dependency parsing reranking achieving competitive performance.