A hybrid filtering approach for question answering
Adafre, Sisay Fissaha and van Genabith, Josef (2009) A hybrid filtering approach for question answering. In: LFG-09 - 14th International Lexical Functional Grammar Conference, 13-16 July 2009, Cambridge, UK.
Full text available as:
We describe a question answering system that took part in the bilingual CLEFQA task
(German-English) where German is the source language and English the target language.We
used the BableFish online translation system to translate the German questions into English.
The system is targeted at Factoid and Denition questions. Our focus in designing the
current system is on testing our online methods which are based on information extraction
and linguistic ltering methods. Our system does not make use of precompiled tables or
Gazetteers but uses Web snippets to rerank candidate answers extracted from the document
collections. WordNet is also used as a lexical resource in the system.
Our question answering system consists of the following core components: Question Anal-
ysis, Passage Retrieval, Sentence Analysis and Answer Selection. These components employ
various Natural Language Processing (NLP) and Machine Learning (ML) tools, a set of
heuristics and dierent lexical resources. Seamless integration of the various components is
one of the major challenges of QA system development. In order to facilitate our develop-
ment process, we used the Unstructured Information Management Architecture (UIMA) as
our underlying framework.
Archive Staff Only: edit this record