| Author | Search for: Li, Junyi Jessy; Search for: Carpuat, Marine1 ; Search for: Nenkova, Ani |
|---|
| Name affiliation | - National Research Council Canada. Information and Communication Technologies
|
|---|
| Format | Text |
|---|
| Type | Article |
|---|
| Proceedings title | 25th International Conference on Computational Linguistics |
|---|
| Conference | 25th International Conference on Computational Linguistics, August 23-29 2014, Dublin, Ireland |
|---|
| ISBN | 978-1-63439-195-5 |
|---|
| Volume | 1 |
|---|
| Pages | 577–586 |
|---|
| Abstract | We present a cross-lingual discourse relation analysis based on a parallel corpus with discourse information available only for one language. First, we conduct a corpus study to explore differences in discourse organization between Chinese and English, including differences in information packaging, implicit/explicit discourse expression divergence, and discourse connective
ambiguities. Second, we introduce a novel approach to learning to recognize discourse relations,
using the parallel corpus instead of discourse annotation in the language of interest. Our resulting
semi-supervised system reaches state-of-art performance on the task of discourse relation
detection, and outperforms a supervised system on discourse relation classification. |
|---|
| Publication date | 2014-10 |
|---|
| Publisher | Association for Computational Linguistics |
|---|
| Terms of use | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| NPARC number | 23000181 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction |
|---|
Record identifier | 0d21da88-d16f-46e9-8f54-faea7be00c89 | | Record created | 2016-06-16 |
|---|
| Record modified | 2016-06-16 |
|---|
