Answering Yes-No Questions by Keyword Distribution: KJP System at NTCIR-11 RITEVal Task

Textual entailment is normally regarded as a deeper analysis issue among other NLP techniques. Most textual entailment approaches employ deeper syntactic and semantic analyses. In contrast to such approaches, we used a simple, but fundamentally important, keyword based technique. Our system architecture was built on our observation that many of textual entailment issues are knowledge search issues, and extracted keyword distribution is the inevitable fundamental basis to solve the problem regardless of methods employed so far.