QALC - the Question-Answering program of the Language and Cognition group at LIMSI-CNRS
نویسندگان
چکیده
In this report we describe the QALC system (the Question-Answering program of the Language and Cognition group at LIMSI-CNRS) which has been involved in the QA-track evaluation at TREC8. The purpose of the Question-Answering track is to nd the answers to a set of 200 questions. The answers are text sequences extracted from the volumes 4 and 5 of the TREC collection. All the questions have at least one answer in the collection. The basic architecture of QALC is composed of ve parallel modules, two for the questions and three for the corpora, and a sixth pairing module which produces the sentences ranked by decreasing order of relevance. Figure 1 illustrates the main components of QALC . More details about each component will be given in the gures corresponding to the detailed descriptions of these subparts. The QALC system relies mainly on genuine Natural Language Processing components. Most of the components rely on a tagged version of the corpus. We use the TreeTagger for this purpose (Stein and Schmid, 1995). The system is based on the following six modules:
منابع مشابه
Finding An Answer Based on the Recognition of the Question Focus
In this report we describe how the QALC system (the Question-Answering program of the LIR group at LIMSI-CNRS, already involved in the QA-track evaluation at TREC9), was improved in order to better extract the very answer in selected sentences. The purpose of the main Question-Answering track in TREC10 was to find text sequences no longer than 50 characters or to produce a "no answer" response ...
متن کاملThe Question Answering System QALC at LIMSI, Experiments in Using Web and WordNet
The QALC question answering system at LIMSI (Ferret et al, 2001) has been largely modified for the TREC11 evaluation campaign. Architecture now includes the processing of answers retrieved from Web searching, and a number of already existing modules has been re-handled. Indeed, introducing the Web as additional resource with regard to the TREC corpus, brought us to experiment comparison strateg...
متن کاملAdaptation of LIMSI's QALC for QA4MRE
In this paper, we present LIMSI participation to one of the pilot tasks of QA4MRE at CLEF 2012: Machine Reading of Biomedical Texts about Alzheimer. For this exercise, we adapted an existing question answering (QA) system, QALC, by searching answers in the reading document. This basic version was used for the evaluation and obtains 0.2, which was increased to 0.325 after basic corrections. We d...
متن کاملDocument selection refinement based on linguistic features for QALC, a Question Answering system
Answering to precise questions requires applying Natural Language techniques in order to locate the answers inside retrieved documents. The QALC system, presented in this paper, participated t o the Question Answering track of the TREC8 and TREC9 evaluations. QALC exploits an analysis of documents based on the search for multi-word terms and their variations. These indexes are used to select a ...
متن کامل