Abstract: | In this paper, we present an evaluation of anaphors generated by a Chinese natural language generation system. In the evaluation work, the anaphors in five test texts generated by three test systems employing generation rules with different complexities were compared with the ones in the same texts created by twelve native speakers of Chinese. We atook the average numbers of anaphors matching etween the machine and human texts as a measure of the quality of anaphors generated by the test systems. The results show that the one we have chosen and which has the most complex rule is better than the other two.
|