No abstract

Abstract. The general aim of the third CLEF Multilingual Question Answering Track was to set up a common and replicable evaluation framework to test both monolingual and cross-language Question Answering (QA) systems that process queries and documents in several European languages. Nine target languages and ten source languages were exploited to enact 8 monolingual and 73 cross-language tasks. Twenty-four groups participated in the exercise. Overall results showed a general increase in performance in comparison to last year. The best performing monolingual system irrespective of target language answered 64.5% of the questions correctly (in the monolingual Portuguese task), while the average of the best performances for each target language was 42.6%. The cross-language step instead entailed a considerable drop in performance. In addition to accuracy, the organisers also measured the relation between the correctness of an answer and a system's stated confidence in it, showing that the best systems did not always provide the most reliable confidence score. We provide an overview of the 2005 QA track, detail the procedure followed to build the test sets and present a general analysis of the results. 308A. Vallin et al.

No abstract

We describe a tool for the development and verification of broad-coverage grammars that are to be used for both analysis and generation. Such a tool is used to ensure that the coverage of the grammar is sufficient (in logical terms the completeness of the grammar) and to control overgeneration (the correctness of the grammar).

We propose a bottom-up variant of Earley deduction. Bottom-up deduction is preferable to topdown deduction because it allows incremental processing (even for head-driven grammars), it is data-driven, no subsumption check is needed, and preference values attached to lexical items can be used to guide bestfirst search. We discuss the scanning step for bottomup Earley deduction and indexing schemes that help avoid useless deduction steps.