Name
Abstract | ||
|---|---|---|
Discourse parsing aims to identify structures and relationships between different discourse units. Most existing approaches analyze a whole discourse at once, which often fails in distinguishing long-span relations and properly representing discourse units. In this article, we propose a novel parsing model to analyze discourse in a two-step fashion with different feature representations to characterize intra sentence and inter sentence discourse structures, respectively. Our model works in a transition-based framework and benefits from a stack long short-term memory neural network model. Experiments on benchmark tree banks show that our method outperforms traditional 1-step parsing methods in both English and Chinese.
|
Year | DOI | Venue |
|---|---|---|
2018 | 10.1145/3152537 | ACM Trans. Asian & Low-Resource Lang. Inf. Process. |
Keywords | Field | DocType |
Discourse parsing, LSTM, dependency parsing, transition-based system | Computer science,Dependency grammar,Artificial intelligence,Natural language processing,Parsing,Artificial neural network,Sentence | Journal |
Volume | Issue | ISSN |
17 | 2 | 2375-4699 |
Citations | PageRank | References |
2 | 0.50 | 28 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yanyan Jia | 1 | 3 | 1.53 |
| Yansong Feng | 2 | 735 | 64.17 |
| Yuan Ye | 3 | 3 | 1.53 |
| Chao Lv | 4 | 14 | 3.16 |
| Chongde Shi | 5 | 3 | 0.86 |
| Dongyan Zhao | 6 | 998 | 96.35 |