xlluis
lsi.upc.edu
Hi! I am Xavier Lluís, a PhD student at the Technical University of Catalonia.
I am a member of the Natural Language Processing Research Group.
My advisor is Lluís Màrquez.
My research is focused on multi-task machine learning applied to natural language problems. I am interested in joint syntactic and shallow semantic parsing. Take a look at the jointparser demo to see joint learning in action.
Have fun!
Email:
xlluislsi.upc.edu
Address:
Office S107 - Omega Building
Campus Nord
Jordi Girona Salgado, 1-3
08034 Barcelona
Abstract: We present a system developed for the CoNLL-2009 Shared Task (Hajic 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.
In Proceedings of the CoNLL-2009 Shared Task [bib].
My Master’s Thesis was defended on September 8th 2008 at the Technical University of Catalonia. It extends the contents of the article A Joint Model for Parsing Syntactic and Semantic Dependencies. slides
Abstract: This paper describes a system that jointly parses syntactic and semantic dependencies, presented at the CoNLL-2008 shared task (Surdeanu et al., 2008). It combines online Perceptron learning (Collins, 2002) with a parsing model based on the Eisner algorithm (Eisner, 1996), extended so as to jointly assign syntacitc and semantic Labels. Overall results are 78.11 global F1 85.84 LAS, 70.35 semantic F1. Official results for the shared task (63.29 global F1; 71.95 LAS; 54.52 semantic F1) were significantly lower due to bugs present at submission time.
In Proceedings of the CoNLL-2008 Shared Task [bib].
The jointparser jointly annotates syntactic and semantic dependencies.