Paper: Improving Text Retrieval Precision and Answer Accuracy in Question Answering Systems

ACL ID W08-1801
Title Improving Text Retrieval Precision and Answer Accuracy in Question Answering Systems
Venue Coling 2008: Proceedings of the workshop on Human Judgements in Computational Linguistics
Session
Year 2008
Authors

Question Answering (QA) systems are of- ten built modularly, with a text retrieval component feeding forward into an answer extraction component. Conventional wis- dom suggests that, the higher the quality of the retrieval results used as input to the an- swer extraction module, the better the ex- tracted answers, and hence system accu- racy, will be. This turns out to be a poor assumption, because text retrieval and an- swer extraction are tightly coupled. Im- provements in retrieval quality can be lost at the answer extraction module, which can not necessarily recognize the additional answer candidates provided by improved retrieval. Going forward, to improve ac- curacy on the QA task, systems will need greater coordination between text retrieval and answer extraction modules.