Abstract | ||
---|---|---|
A lack of labeled corpora obstructs the research progress on implicit discourse relation recognition (DRR) for Chinese, while there are some available discourse corpora in other languages, such as English. In this paper, we propose a cross-lingual implicit DRR framework that exploits an available English corpus for the Chinese DRR task. We use machine translation to generate Chinese instances from a labeled English discourse corpus. In this way, each instance has two independent views: Chinese and English views. Then we train two classifiers in Chinese and English in a co-training way, which exploits unlabeled Chinese data to implement better implicit DRR for Chinese. Experimental results demonstrate the effectiveness of our method. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1631/FITEE.1601865 | Frontiers of IT & EE |
Keywords | Field | DocType |
Cross-lingual, Implicit discourse relation recognition, Co-training, TP391.1 | Discourse relation,Mathematical optimization,Cross lingual,Computer science,Machine translation,Co-training,Exploit,Natural language processing,Artificial intelligence | Journal |
Volume | Issue | ISSN |
19 | 5 | 2095-9184 |
Citations | PageRank | References |
1 | 0.35 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yaojie Lu | 1 | 3 | 3.42 |
mu xu | 2 | 5 | 10.29 |
ChangXing Wu | 3 | 7 | 2.11 |
Deyi Xiong | 4 | 845 | 67.74 |
Hongji Wang | 5 | 9 | 1.12 |
Jinsong Su | 6 | 260 | 41.51 |