2. Parsing Model 3

Abstract not found

Abstract not found

This paper presents some statistics on an implementation of Joakim Nivre's algorithm. The implementation in Prolog have a coverage of 100% because of the backtracking mechanism in Prolog. The rank of the correct graph within all produced graphs are not very good with this implementation

Abstract not found

Abstract not found

The arc-eager system for transition-based dependency parsing is widely used in natural language processing despite the fact that it does not guarantee that the output is a well-formed dependency tree. We propose a simple modification to the original system that enforces the tree constraint without requiring any modification to the parser training procedure. Experiments on multiple languages show that the method on average achieves 72 % of the error reduction possible and consistently outperforms the standard heuristic in current use. 1.

Abstract not found

In most fields within computer linguistics it is essential to have access to highquality syntactic parsing. During the previous 10-15 years great improvements have been made in development of parsing algorithms. Increasingly, the approach is to use algorithms to train the parser from annotated text samples. This report studies one of the most successful parser algorithms and explores methods of how to find optimal training parameters. Sammanfattning För de flesta områden inom datalingvistiken är det av avgörande betydelse att ha tillgång till en syntaktisk parser med hög prestanda. De senaste 10–15 åren har stora framgångar uppnåtts inom utvecklandet av parseralgoritmer. I allt högre grad används tillvägagångssättet att träna parsern med exempel av uppmärkt text. I denna rapport studeras en av de mest framgångsrika parseralgoritmerna och undersöker olika sätt att finna de bästa parametrarna för träning. Contents

Each year the Conference on Computational Natural Language Learning (CoNLL) 1 features a shared task, in which participants train and test their systems on exactly the same data sets, in order to better compare systems. The tenth CoNLL (CoNLL-X) saw a shared task on Multilingual Dependency Parsing. In this paper, we describe how treebanks for 13 languages were converted into the same dependency format and how parsing performance was measured. We also give an overview of the parsing approaches that participants took and the results that they achieved. Finally, we try to draw general conclusions about multi-lingual parsing: What makes a particular language, treebank or annotation scheme easier or harder to parse and which phenomena are challenging for any dependency parser? Acknowledgement Many thanks to Amit Dubey and Yuval Krymolowski, the other two organizers of the shared task, for discussions, converting treebanks, writing software and helping with the papers. 2