1 QUESTION SEARCHART TECHNIQUES USUALLY FAIL TO ACHIEVE DESIRED RESU...

2.1 Question Search

art techniques usually fail to achieve desired results

due to short questions and information need texts.

Burke et al. (1997) combined a lexical metric and a

simple semantic knowledge-based (WordNet) simi-

In order to measure the similarity between short

texts, we make use of three kinds of text similari-

larity method to retrieve semantically similar ques-

tions from frequently asked question (FAQ) data.

ty measures: TFIDF based, Knowledge based and

Latent Dirichlet Allocation (LDA) based similarity

Jeon et al. (2005a) retrieved semantically similar

measures in this paper. We will compare their per-

questions from Korean CQA data by calculating the

formance for the task of question recommendation

similarity between their answers. The assumption

in the experiment section.

behind their research is that questions with very sim-

ilar answers tend to be semantically similar. Jeon