Paper Info
Title
A Trainable Multi-factored QA System.
Abstract
This paper reports on the construction and testing of a new Question Answering (QA) system, implemented as an workflow which builds on several web services developed at the Research Institute for Artificial Intelligence (RACAI).The evaluation of the system has been independently done by the organizers of the Romanian-Romanian task of the ResPubliQA 2009 exercise and has been rated the best performing system with the highest improvement due to the NLP technology over a baseline state-of-the-art IR system. We describe a principled way of combining different relevance measures for obtaining a general relevance (to the user’s question) score that will serve as the sort key for the returned paragraphs. The system was trained on a specific corpus, but its functionality is independent on the linguistic register of the training data. The trained QA system that participated in the ResPubliQA shared task is available as a web application at http://www2.racai.ro/sir-resdec/ .
Year
DOI
Venue
2009
10.1007/978-3-642-15754-7_29
CLEF (Working Notes)
Keywords
Field
DocType
artificial intelligence,different relevance measure,research institute,romanian-romanian task,baseline state-of-the-art ir system,trained qa system,nlp technology,web application,web service,general relevance,artificial intelligent,question answering
Training set,Content word,Question answering,Information retrieval,Computer science,sort,Natural language processing,Artificial intelligence,Web application,Web service,Workflow
Conference
Volume
ISSN
ISBN
6241
0302-9743
3-642-15753-X
Citations 
PageRank 
References 
7
0.93
11
Authors
6
Name
Order
Citations
PageRank
Radu Ion116322.33
Dan Ştefánescu213614.65
Alexandru Ceauşu3709.36
Dan Tufis448558.39
Elena Irimia5246.76
Verginica Barbu Mititelu62511.35