This paper describes the systems of THU QUANTA in Text Analysis Conference (TAC) 2008. We participated in the Question Answering (QA) track, and the Recognizing Textual Entailment (RTE) track. For question answering track, we enhanced the traditional question answering system by sentiment lexicon based opinion analysis. The rigid list questions are divided into two categories based on their answer types. And two snippet extraction approaches are proposed to answer squishy list questions. For

more »

... track, we design different strategies to recognize true entailment and false entailment. The similarity between hypothesis and text is measured to recognize true entailment. We detect the exact entity and relation mismatch to recognize the false entailment. The evaluation results show that the proposed approaches are very effective for the QA and RTE tasks.