1 FEATURE EXTRACTIONANSWER CANDIDATE EXTRACTION IS ALSO A CLASSIFICA...

3.1 Feature Extraction

Answer candidate extraction is also a classifica-

This paper employs three groups of features as fea-

tion problem that classifies words into answer types

tures of input data:

(i.e., question types), such as

,

, and

. Answer selection is an exactly classifica-

• Question Feature Set (QF);

tion that classifies answer candidates as positive or

negative. Therefore, we can apply machine learning

• Document Feature Set (DF);

techniques to generate classifiers that work as com-

• Combined Feature Set (CF), i.e., combinations

ponents of a QA system.

of question and document features.

In the QBTE approach, these three components,

i.e., question analysis, answer candidate extraction,

3