Corpus-based Generation of Easy Help-desk Responses

We present a corpus-based approach for the automatic generation of email responses to helpdesk requests. This is largely an extractive multi-document summarization task. However, in our application users have a very low tolerance for responses that contain incongruous sentences. To address this problem, we propose a method for extracting high-precision sentences for inclusion in a response, and a measure for predicting the completeness of a planned response. The idea is that complete, high-precision responses may be sent to users, while incomplete responses should be passed to operators. Our results show that a small but significant proportion (14%) of our automatically generated responses have a high degree of precision and completeness, and that our measure can reliably predict the completeness of a response.