Monday, 2 March, 2020 - 14:00
Room: 

Cross-lingual search in medical texts

Shadi Saleh (ÚFAL MFF UK)

In this talk, we will present the problem of Cross-lingual Information Retrieval (CLIR) in medical texts and show our contribution to the research in this area. The goal of this task is to find documents in a given language relevant to queries formulated in a different language. Our experiments are conducted using the CLEF eHealth collection containing medical articles in English and queries in Czech, French, German, Hungarian, Polish, Spanish, Swedish. In our work we explore the two main approaches to this task: Document Translation and Query Translation. We exploit both the Statistical Machine and Neural Machine Translation paradigms, and methods for query translation reranking and expansion.