Clustering Based Question Set Generation for Training and Testing of a Question and Answer System

摘要

Mechanisms for selecting questions for a cluster of questions to be used with a question and answer (QA) system are provided. An input question is received and analyzed to identify at least one feature of the input question. Clustering of the input question with one or more other questions in a cluster of questions based on the at least one feature of the input question is performed. Based on results of the clustering, a determination is made as to whether to include or reject the input question as part of the cluster of questions. In response to determining to include the input question as part of the cluster of questions, the cluster of questions is updated to include the input question. The updated cluster of questions is stored in a storage device associated with a data processing system.

主权项

1. A method, in a data processing system comprising a processor and a memory, for selecting questions for a cluster of questions to be used with a question and answer (QA) system, the method comprising:
receiving, in the data processing system, an input question; analyzing, by the data processing system, the input question to identify at least one feature of the input question; performing, by the data processing system, clustering of the input question with one or more other questions in a cluster of questions based on the at least one feature of the input question; determining, by the data processing system, based on results of the clustering, whether to include or reject the input question as part of the cluster of questions; in response to determining to include the input question as part of the cluster of questions, updating, by the data processing system, the cluster of questions to include the input question; and storing, by the data processing system, the updated cluster of questions in a storage device associated with the data processing system.