Abstract
Existing works indicate that the absence of explicit discourse connectives makes it difficult to recognize implicit discourse relations. In this paper we attempt to overcome this difficulty for implicit relation recognition by automatically inserting discourse connectives between arguments with the use of a language model. Then we propose two algorithms to leverage the information of these predicted connectives. One is to use these predicted implicit connectives as additional features in a supervised model. The other is to perform implicit relation recognition based only on these predicted connectives. Results on Penn Discourse Treebank 2.0 show that predicted discourse connectives help implicit relation recognition and the first algorithm can achieve an absolute average f-score improvement of 3% over a state of the art baseline system.
| Original language | English |
|---|---|
| Pages | 1507-1514 |
| Number of pages | 8 |
| State | Published - 2010 |
| Externally published | Yes |
| Event | 23rd International Conference on Computational Linguistics, Coling 2010 - Beijing, China Duration: 23 Aug 2010 → 27 Aug 2010 |
Conference
| Conference | 23rd International Conference on Computational Linguistics, Coling 2010 |
|---|---|
| Country/Territory | China |
| City | Beijing |
| Period | 23/08/10 → 27/08/10 |