| Author | Search for: Zhu, Xiaodan1; Search for: Sobhani, Parinaz; Search for: Guo, Hongyu1 |
|---|
| Affiliation | - National Research Council of Canada. Information and Communication Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 32nd International Conference on Machine Learning, July 6-11, 2015, Lille, France |
|---|
| Subject | artificial intelligence; brain; computational linguistics; semantics; speech recognition; speech transmission; trees (mathematics); composition layers; long distance interactions; long short term memory; machine translations; natural language understanding; recursive modeling; recursive structure; semantic composition; learning systems |
|---|
| 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-the-art 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. |
|---|
| Publication date | 2016-03 |
|---|
| Publisher | International Machine Learning Society |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| NPARC number | 23000279 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 3f52b3f9-330f-4ca8-95b8-1c3a68fc4fa7 |
|---|
| Record created | 2016-07-04 |
|---|
| Record modified | 2020-03-16 |
|---|
