Name
Abstract | ||
|---|---|---|
Identifying long-span dependencies between discourse units is crucial to improve discourse parsing performance. Most existing approaches design sophisticated features or exploit various off-the-shelf tools, but achieve little success. In this paper, we propose a new transition-based discourse parser that makes use of memory networks to take discourse cohesion into account. The automatically captured discourse cohesion benefits discourse parsing, especially for long span scenarios. Experiments on the RST discourse treebank show that our method outperforms traditional featured based methods, and the memory based discourse cohesion can improve the overall parsing performance significantly (1). |
Year | Venue | Field |
|---|---|---|
2018 | PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 | Cohesion (chemistry),Computer science,Artificial intelligence,Natural language processing,Parsing |
DocType | Volume | Citations |
Conference | P18-2 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yanyan Jia | 1 | 3 | 1.53 |
| Yuan Ye | 2 | 3 | 1.53 |
| Yansong Feng | 3 | 735 | 64.17 |
| Yuxuan Lai | 4 | 2 | 2.39 |
| Rui Yan | 5 | 961 | 76.69 |
| Dongyan Zhao | 6 | 998 | 96.35 |