# Improving Tree-LSTM with Tree Attention

arXiv: https://arxiv.org/abs/1901.00066 · HTML: https://mlsanity.com/paper/1901.00066/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jan 2019.

## Built on by (most cited first, 6 of 6)

- [Uncertainty in Natural Language Generation: From Theory to Applications](https://mlsanity.com/paper/2307.15703/) (2023)
- [Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2109.00269/) (2021)
- [PETCI: A Parallel English Translation Dataset of Chinese Idioms](https://mlsanity.com/paper/2202.09509/) (2022)
- [Corpus-Based Paraphrase Detection Experiments and Review](https://mlsanity.com/paper/2106.00145/) (2021)
- [Database Workload Characterization with Query Plan Encoders](https://mlsanity.com/paper/2105.12287/) (2021)
- [Structured Prediction in NLP -- A survey](https://mlsanity.com/paper/2110.02057/) (2021)

## Abstract (arXiv)

In Natural Language Processing (NLP), we often need to extract information from tree topology. Sentence structure can be represented via a dependency tree or a constituency tree structure. For this reason, a variant of LSTMs, named Tree-LSTM, was proposed to work on tree topology. In this paper, we design a generalized attention framework for both dependency and constituency trees by encoding variants of decomposable attention inside a Tree-LSTM cell. We evaluated our models on a semantic relatedness task and achieved notable results compared to Tree-LSTM based methods with no attention as well as other neural and non-neural methods and good results compared to Tree-LSTM based methods with attention.