DMCA
Long short-term memory over recursive structures. (2015)
| Venue: | In Proceedings of the 32nd International Conference on Machine Learning (ICML-15), |
| Citations: | 2 - 0 self |
BibTeX
@INPROCEEDINGS{Zhu15longshort-term,
author = {Xiaodan Zhu and Parinaz Sobhani and Psobh090@uottawa Ca and Hongyu Guo},
title = {Long short-term memory over recursive structures.},
booktitle = {In Proceedings of the 32nd International Conference on Machine Learning (ICML-15),},
year = {2015},
pages = {1604--1612}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract The chain-structured long short-term memory (LSTM) has showed to be effective in a wide range of problems such as speech recognition and machine translation. In this paper, we propose to extend it to tree structures, in which a memory cell can reflect the history memories of multiple child cells or multiple descendant cells in a recursive process. We call the model S-LSTM, which provides a principled way of considering long-distance interaction over hierarchies, e.g., language or image parse structures. We leverage the models for semantic composition to understand the meaning of text, a fundamental problem in natural language understanding, and show that it outperforms a state-of-theart recursive model by replacing its composition layers with the S-LSTM memory blocks. We also show that utilizing the given structures is helpful in achieving a performance better than that without considering the structures.
