Creating the DISEQuA Corpus: A Test Set for Multilingual Question Answering

Abstract

This paper describes the procedure adopted by the three co-ordinators of the CLEF 2003 question answering track (ITC-irst, UNED and ILLC) to create the question set for the monolingual tasks. Despite the little resources available, the three groups collaborated and managed to formulate and verify a large pool of original questions posed in three different languages: Dutch, Italian and Spanish. A part of these queries was translated into English and shared between the three coordination groups. Thus, a second cross-verification was conducted, in order to extract the queries that had an answer in all the three monolingual document collections. Finally, the result of the joint efforts was the creation of the DISEQuA (Dutch Italian Spanish English Questions and Answers) corpus, a useful and reusable resource that is freely available for the research community. The article reports on the different stages of the corpus creation, from the monolingual kernels to the multilingual extension.

Directions for exploiting asymmetries in multilingual Wikipedia

“…Corpora developed for multilingual and crosslingual question-answering (QA), information retrieval (IR), and information extraction (IE) tasks are typically compilations of documents on related subjects written in different languages. Documents in such corpora rarely have counterparts in all the languages presented in the corpus (CLEF, 2000;Magnini et al, 2003).…”

Question Classification in Spanish and Portuguese

“…The data set used in this work consists of the questions provided in the DISEQuA Corpus [10]. Such corpus was made up of simple, mostly short, straightforward and factual queries that sound naturally spontaneous, and arisen from a real desire to know something about a particular event or situation.…”

A language independent method for question classification

“…The data set used in this work consists of the questions provided in the DISEQuA Corpus (Magnini et al, 2003). Such corpus was made up of simple, mostly short, straightforward and factual queries that sound naturally spontaneous, and arisen from a real desire to know something about a particular event or situation.…”