For the 11th straight year, the Conference on Computational Natural Language Learning has been accompanied by a shared task whose purpose is to promote natural language processing applications and evaluate them in a standard setting. In 2009, the shared task was dedicated to the joint parsing of syntactic and semantic dependencies in multiple languages. This shared task combines the shared tasks of the previous five years under a unique dependency-based formalism similar to the 2008 task. In this paper, we define the shared task, describe how the data sets were created and show their quantitative properties, report the results and summarize the approaches of the participating systems.

We propose a system to carry out the joint parsing of syntactic and semantic dependencies in multiple languages for our participation in the shared task of CoNLL-2009. We present an iterative approach for dependency parsing and semantic role labeling. We have participated in the closed challenge, and our system achieves 73.98 % on labeled macro F1 for the complete problem, 77.11 % on labeled attachment score for syntactic dependencies, and 70.78 % on labeled F1 for semantic dependencies. The current experimental results show that our method effectively improves system performance. 1

We present a system developed for the CoNLL-2009 Shared Task (Hajič et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the built tree in second-order factors. We include semantic dependencies in the factors and extend their score function to combine syntactic and semantic scores. The parser is coupled with an on-line averaged perceptron (Collins, 2002) as the learning method. Our averaged results for all seven languages are 71.49 macro F1, 79.11 LAS and 63.06 semantic F1. 1

We present the Crotal system, used in the CoNLL09 Shared Task. It is based on XCRF, a highly configurable CRF library which can take into account hierarchical relations. This system had never been used in such a context thus the performance is average, but we are

Motivated by the large number of languages (seven) and the short development time (two months) of the 2009 CoNLL shared task, we exploited latent variables to avoid the costly process of hand-crafted feature engineering, allowing the latent variables to induce features from the data. We took a pre-existing generative latent variable model of joint syntacticsemantic dependency parsing, developed for English, and applied it to six new languages with minimal adjustments. The parser’s robustness across languages indicates that this parser has a very general feature set. The parser’s high performance indicates that its latent variables succeeded in inducing effective features. This system was ranked third overall with a macro averaged F1 score of 82.14%, only 0.5 % worse than the best system. 1

This paper describes our contribution to the semantic role labeling task (SRL-only) of the CoNLL-2009 shared task in the closed challenge (Hajič et al., 2009). Our system consists of a pipeline of independent, local classifiers that identify the predicate sense, the arguments of the predicates, and the argument labels. Using these local models, we carried out a beam search to generate a pool of candidates. We then reranked the candidates using a joint learning approach that combines the local models and proposition features. To address the multilingual nature of the data, we implemented a feature selection procedure that systematically explored the feature space, yielding significant gains over a standard set of features. Our system achieved the second best semantic score overall with an average labeled semantic F1 of 80.31. It obtained the best F1 score on the Chinese and German data and the second best one on English. 1

Thesis for a diploma in computer science, 30 ECTS credits

This paper describes a system for syntacticsemantic dependency parsing for multiple languages. The system consists of three parts: a state-of-the-art higher-order projective dependency parser for syntactic dependency parsing, a predicate classifier, and an argument classifier for semantic dependency parsing. For semantic dependency parsing, we explore use of global features. All components are trained with an approximate max-margin learning algorithm. In the closed challenge of the CoNLL-2009 Shared Task (Hajič et al., 2009), our system achieved the 3rd best performances for English and Czech, and the 4th best performance for Japanese. 1

In this paper we present two approaches to automatically extract cross-lingual predicate clusters, based on bilingual parallel corpora and cross-lingual information extraction. We demonstrate how these clusters can be used to improve the NIST Automatic Content Extraction (ACE) event extraction task 1. We propose a new inductive learning framework to automatically augment background data for lowconfidence events and then conduct global inference. Without using any additional data or accessing the baseline algorithms this approach obtained significant improvement over a state-of-the-art bilingual (English and Chinese) event extraction system. 1

I describe a fast multilingual parser for semantic dependencies. The parser is implemented as a pipeline of linear classifiers trained with support vector machines. I use only first order features, and no pair-wise feature combinations in order to reduce training and prediction times. Hyper-parameters are carefully tuned for each language and sub-problem. The system is evaluated on seven different