In this paper, we present a discriminative approach for reranking discourse trees generated by an existing probabilistic discourse parser. The reranker relies on tree kernels (TKs) to capture the global dependencies between discourse units in a tree. In particular, we design new computational structures of discourse trees, which combined with standard TKs, originate novel discourse TKs. The empirical evaluation shows that our reranker can improve the state-of-the-art sentence-level parsing accuracy from 79.77% to 82.15%, a relative error reduction of 11.8%, which in turn pushes the state-of-the-art documentlevel accuracy from 55.8% to 57.3%.

@inproceedings{joty-moschitti-emnlp-14, abstract = {In this paper, we present a discriminative approach for reranking discourse trees generated by an existing probabilistic discourse parser. The reranker relies on tree kernels (TKs) to capture the global dependencies between discourse units in a tree. In particular, we design new computational structures of discourse trees, which combined with standard TKs, originate novel discourse TKs. The empirical evaluation shows that our reranker can improve the state-of-the-art sentence-level parsing accuracy from 79.77% to 82.15%, a relative error reduction of 11.8%, which in turn pushes the state-of-the-art documentlevel accuracy from 55.8% to 57.3%.}, address = {Doha, Qatar}, author = {Joty, Shafiq and Moschitti, Alessandro}, booktitle = {Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing}, month = {October}, pages = {2049--2060}, publisher = {ACL}, series = {EMNLP'14}, title = {Discriminative Reranking of Discourse Parses Using Tree Kernels}, url = {http://www.aclweb.org/anthology/D14-1219}, year = {2014} }