@inProceedings{Ghosh-Sucheta2011-151350, title = {End-to-End Discourse Parser Evaluation}, abstract = {We are interested in the problem of discourse parsing of textual documents. We present a novel end-to-end discourse parser that, given a plain text document in input, identifies the discourse relations in the text, assigns them a semantic label and detects discourse arguments spans. The parsing architecture is based on a cascade of decisions supported by Conditional Random Fields (CRF). We train and evaluate three different parsers using the PDTB corpus. The three system versions are compared to evaluate their robustness with respect to deep/shallow and automatically extracted syntactic features.}, booktitle = {Fifth IEEE International Conference on Semantic Computing (ICSC), 2011; September 18-21, 2011; Palo Alto, United States}, author = {Ghosh, Sucheta and Tonelli, Sara and Riccardi, Giuseppe and Johansson, Richard}, year = {2011}, ISBN = {978-1-4577-1648-5}, pages = {169--172}, } @inProceedings{Ghosh-Sucheta2011-151356, title = {Shallow Discourse Parsing with Conditional Random Fields}, abstract = {Parsing discourse is a challenging natural language processing task. In this paper we take a data driven approach to identify arguments of explicit discourse connectives. In contrast to previous work we do not make any assumptions on the span of arguments and consider parsing as a token-level sequence labeling task. We design the argument segmentation task as a cascade of decisions based on conditional random fields (CRFs). We train the CRFs on lexical, syntactic and semantic features extracted from the Penn Discourse Treebank and evaluate feature combinations on the commonly used test split. We show that the best combination of features includes syntactic and semantic features. The comparative error analysis investigates the performance variability over connective types and argument positions.}, booktitle = {Proceedings of 5th International Joint Conference on Natural Language Processing; editors Haifeng Wang and David Yarowsky; Chiang Mai, Thailand; November 8-13, 2011}, author = {Ghosh, Sucheta and Johansson, Richard and Riccardi, Giuseppe and Tonelli, Sara}, year = {2011}, pages = {1071--1079}, } @inProceedings{Ju-Qi2011-151361, title = {Towards Using Reranking in Hierarchical Classification}, abstract = {We consider the use of reranking as a way to relax typical in- dependence assumptions often made in hierarchical multilabel classification. Our reranker is based on (i) an algorithm that generates promising k-best classification hypotheses from the output of local binary classifiers that clas- sify nodes of a target tree-shaped hierarchy; and (ii) a tree kernel-based reranker applied to the classification tree associated with the hypotheses above. We carried out a number of experiments with this model on the Reuters corpus: we firstly show the potential of our algorithm by computing the oracle classification accuracy. This demonstrates that there is a signifi- cant room for potential improvement of the hierarchical classifier. Then, we measured the accuracy achieved by the reranker, which shows a significant performance improvement over the baseline. }, booktitle = {Proceedings of the Joint ECML/PKDD-PASCAL Workshop on Large-Scale Hierarchical Classification; September 5, 2011; Athens, Greece}, author = {Ju, Qi and Johansson, Richard and Moschitti, Alessandro}, year = {2011}, }