TITLE: Cross-Language Information Retrieval and Cross-Language Plagiarism Analysis
SPEAKER: Viviane Moreira (Instituto de Informatica - UFRGS, Porto Alegre/RS, Brasil)

ABSTRACT:

Cross-Language Information Retrieval (CLIR) is the retrieval of documents in one natural language, based on a query formulated in another natural language, e.g. retrieval of documents written in English based on a set of keywords in Spanish. The talk will start with a brief introduction to the research area, followed by a report on an approach for CLIR that uses algorithms for mining association rules. These algorithms have been widely used to analyse market basket data. The idea is to map the problem of finding associations between sales items to the problem of finding term translations over a parallel corpus.

The second part of the talk will discuss Cross-Language Plagiarism Analysis (CLPA), which aims at detecting plagiarized passages in the suspicious documents and their corresponding text fragments in the a reference collection even if these documents are in different languages. CLPA and CLIR are related topics, but the problem of CLPA is more difficult as it is necessary to match a segment of text in one language to a segment of text of equal content in another language. The talk will describe ongoing work on a CLPA method.