Cross-Lingual Word Sense Disambiguation Using Multilingual Co-occurrence Graphs Simone Paolo Ponzetto and Carina Silberer We present the University of Heidelberg (UHD) system that participated in the Cross-Lingual Word Sense Disambiguation SemEval-2010 task (CL-WSD). Our system performs CL-WSD -- i.e. the task of disambiguating a word in context by providing its most appropriate translations in different languages -- by applying graph algorithms previously developed for monolingual WSD to multilingual co-occurrence graphs. UHD has participated in the Best and out-of-five (OOF) evaluations and ranked among the most competitive systems for this task, thus indicating that graph-based approaches represent indeed a powerful alternative. We start by introducing the task of CL-WSD and its motivation, i.e. the need for WSD to be integrated within end-user applications such as Machine Translation or multilingual Information Retrieval. We then present in detail the methodology used in our system, which performs CL-WSD on multilingual graphs automatically induced from the target words' aligned contexts found in parallel corpora such as Europarl and JRC-Aquis. We finally conclude with a variety of remarks on how to extend our preliminary work, most notably by relying on better multilingual resources and more robust algorithms better tailored for the multilingual task at hand.