Improving Tree-LSTM with Tree Attention
Abstract
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.
Keywords
Cite
@article{arxiv.1901.00066,
title = {Improving Tree-LSTM with Tree Attention},
author = {Mahtab Ahmed and Muhammad Rifayat Samee and Robert E. Mercer},
journal= {arXiv preprint arXiv:1901.00066},
year = {2019}
}
Comments
8 Pages, 3 figures, Accepted in The 13th IEEE International Conference on Semantic Computing (ICSC 2019)