RACAI's Question Answering System at QA@CLEF 2007
نویسندگان
چکیده
This paper presents a pattern-based question answering system for the Romanian-Romanian task of the Multiple Language Question Answering (QA@CLEF) track of the CLEF 2007 campaign. We show that working with a good Boolean searching engine and using question type driven answer extraction heuristics, one can achieve acceptable results (30% overall accuracy) using simple, pattern-based techniques. Furthermore, we will present an answer extraction algorithm that aims at finding the correct answer irrespective of the question and answer type.
منابع مشابه
RACAI's QA System at the Romanian-Romanian Multiple Language Question Answering (QA@CLEF2008) Main Task
This paper describes the participation of the Research Institute for Artificial Intelligence, Romanian Academy (RACAI) to the Multiple Language Question Answering Main Task at the CLEF 2008 competition. We present our Question Answering system answering Romanian questions from Romanian Wikipedia documents focusing on the implementation details. The presentation will also emphasize the fact that...
متن کاملRACAI's QA System at the Romanian-Romanian QA@CLEF2008 Main Task
This paper describes the participation of the Research Institute for Artificial Intelligence of the Romanian Academy (RACAI) to the Multiple Language Question Answering Main Task at the CLEF 2008 competition. We present our Question Answering system answering Romanian questions from Romanian Wikipedia documents focusing on the implementation details. The presentation will also emphasize the fac...
متن کاملMultilingual Question Answering through Intermediate Translation: LCC's PowerAnswer at QA@CLEF 2007
This paper reports on Language Computer Corporation’s QA@CLEF 2007 preparation, participation and results. For this exercise, LCC integrated its open-domain PowerAnswer Question Answering system with its statistical Machine Translation engine. For 2007, LCC participated in the English-to-French and English-to-Portuguese crosslanguage tasks. The approach is that of intermediate translation, only...
متن کاملQA@L2F, First Steps at QA@CLEF
This paper presents QA@LF, the question-answering system developed at LF, INESC-ID. QA@LF follows different strategies according with the question type, and relies strongly on named entity recognition and on the pre-detection of linguistic patterns. Each question type is mapped into a single strategy; however, if no answer is found, the system proceeds and tries to find an answer using one of t...
متن کاملMaking RAPOSA (FOX) Smarter
In this paper we describe RAPOSA, a question answering system for Portuguese, and we present detailed results of the participation in the QA@CLEF 2007 evaluation task. We explain how we improved our system since the last participation in QA@CLEF, by expanding the set of rules associated with Question Parsing and Answering Extraction. We will finish by pointing lines for future work, and by intr...
متن کامل