论文信息 - Qa@l2f@qa@clef

Qa@l2f@qa@clef

This paper introduces L2F’s (INESC-ID) question/answering system and presents its results in the QA@CLEF07 evaluation task. QA@LF bases its performance on a high-quality deep linguistic analysis of the question, which is strongly based on named entity recognition. However, if a precise analysis is not possible or if no answer is found in previous processed data, the system is also capable of relaxing and tries to find an answer using a flexible pattern matching approach.

[1] Jean-Pierre Chanod,et al. A Multi-Input Dependency Parser , 2001, IWPT.

[2] Adán Cassan,et al. Priberam's Question Answering System in a Cross-Language Environment , 2006, CLEF.

[3] Luís Sarmento. Hunting Answers with RAPOSA (FOX) , 2006, CLEF.

[4] Ricardo Ribeiro,et al. Using Morphossyntactic Information in TTS Systems: Comparing Stratgies for European Portuguese , 2003, PROPOR.

[5] A. Karimi,et al. Master‟s thesis , 2011 .

[6] Joana L. Paulo. Terms Spotting with Linguistics and Statistics , 2004 .

[7] Luís Costa. Esfinge - a Modular Question Answering System for Portuguese , 2006, CLEF.