Abstract
We address the problem of ordering several circumstantials when generating or revising a clause. This problem occurs in the context of a multi-document summarization system that relies on language generation to incrementally reformulate the wording of fragments of sentences extracted from the documents.
We present the results of an extensive corpus analysis of the relative position of different types of circumstantials. Our approach learns a set of rules using parameters that can be effectively used by our
system. Evaluation indicates that these rules, which we have implemented in our text generator, attain a high level of precision (95.4%
over a baseline of 78.6%).
We present the results of an extensive corpus analysis of the relative position of different types of circumstantials. Our approach learns a set of rules using parameters that can be effectively used by our
system. Evaluation indicates that these rules, which we have implemented in our text generator, attain a high level of precision (95.4%
over a baseline of 78.6%).
| Original language | English GB |
|---|---|
| Title of host publication | In Proceedings of BISFAI'01, June 2001 |
| State | Published - 2001 |