We present a comparative study of corpus-based methods for the automatic synthesis of email responses to help-desk requests. Our methods were developed by considering two operational dimensions: (1) information-gathering technique, and (2) granularity of the information. In particular, we investigate two techniques -- retrieval and prediction -- applied to information represented at two levels of granularity -- sentence level and document level. We also developed a hybrid method that combines prediction with retrieval. Our results show that the different approaches are applicable in different situations, addressing a combined 72\% of the requests with either complete or partial responses.
The paper is available as gzipped postscript (20 kB) and pdf (32 kB).
Also available on the Springer-Verlag website here.
Alternatively, you can request a copy by e-mailing me.