Abstract
Two of the main corpora available for training discourse relation classifiers are the RST Discourse Treebank (RST-DT) and the Penn Discourse Treebank (PDTB), which are both based on the Wall Street Journal corpus. Most recent work using discourse relation classifiers have employed fully-supervised methods on these corpora. However, certain discourse relations have little labeled data, causing low classification performance for their associated classes. In this paper, we attempt to tackle this problem by employing a semi-supervised method for discourse relation classification. The proposed method is based on the analysis of feature cooccurrences in unlabeled data. This information is then used as a basis to extend the feature vectors during training. The proposed method is evaluated on both RST-DT and PDTB, where it significantly outperformed baseline classifiers. We believe that the proposed method is a first step towards improving classification performance, particularly for discourse relations lacking annotated data.
Original language | English |
---|---|
Title of host publication | Proceedings of the SIGDIAL 2010 Conference: 11th Annual Meeting of the Special Interest Group onDiscourse and Dialogue |
Pages | 55-58 |
Number of pages | 4 |
Publication status | Published - 2010 |
Externally published | Yes |
Event | 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2010 - Tokyo Duration: 2010 Sep 24 → 2010 Sep 25 |
Other
Other | 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2010 |
---|---|
City | Tokyo |
Period | 10/9/24 → 10/9/25 |
Fingerprint
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition
- Human-Computer Interaction
- Modelling and Simulation
Cite this
Towards semi-supervised classification of discourse relations using feature correlations. / Hernault, Hugo; Bollegala, Danushka; Ishizuka, Mitsuru.
Proceedings of the SIGDIAL 2010 Conference: 11th Annual Meeting of the Special Interest Group onDiscourse and Dialogue. 2010. p. 55-58.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Towards semi-supervised classification of discourse relations using feature correlations
AU - Hernault, Hugo
AU - Bollegala, Danushka
AU - Ishizuka, Mitsuru
PY - 2010
Y1 - 2010
N2 - Two of the main corpora available for training discourse relation classifiers are the RST Discourse Treebank (RST-DT) and the Penn Discourse Treebank (PDTB), which are both based on the Wall Street Journal corpus. Most recent work using discourse relation classifiers have employed fully-supervised methods on these corpora. However, certain discourse relations have little labeled data, causing low classification performance for their associated classes. In this paper, we attempt to tackle this problem by employing a semi-supervised method for discourse relation classification. The proposed method is based on the analysis of feature cooccurrences in unlabeled data. This information is then used as a basis to extend the feature vectors during training. The proposed method is evaluated on both RST-DT and PDTB, where it significantly outperformed baseline classifiers. We believe that the proposed method is a first step towards improving classification performance, particularly for discourse relations lacking annotated data.
AB - Two of the main corpora available for training discourse relation classifiers are the RST Discourse Treebank (RST-DT) and the Penn Discourse Treebank (PDTB), which are both based on the Wall Street Journal corpus. Most recent work using discourse relation classifiers have employed fully-supervised methods on these corpora. However, certain discourse relations have little labeled data, causing low classification performance for their associated classes. In this paper, we attempt to tackle this problem by employing a semi-supervised method for discourse relation classification. The proposed method is based on the analysis of feature cooccurrences in unlabeled data. This information is then used as a basis to extend the feature vectors during training. The proposed method is evaluated on both RST-DT and PDTB, where it significantly outperformed baseline classifiers. We believe that the proposed method is a first step towards improving classification performance, particularly for discourse relations lacking annotated data.
UR - http://www.scopus.com/inward/record.url?scp=84857740734&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84857740734&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84857740734
SN - 9781932432855
SP - 55
EP - 58
BT - Proceedings of the SIGDIAL 2010 Conference: 11th Annual Meeting of the Special Interest Group onDiscourse and Dialogue
ER -