Identification of Speakers in Novels

Speaker identification is the task of attributing utterances to characters in a literary narrative. It is challenging to automate because the speakers of the majority of utterances are not explicitly identified in novels. In this paper, we present a supervised machine learning approach for the task that incorporates several novel features. The experimental results show that our method is more accurate and general than previous approaches to the problem.

Acknowledgments

We would like to thank Asli Celikyilmaz for collaboration in the early stages of this project, Susan Brown and Michelle Di Cintio for help with data annotation, and David Elson for the attempt to compute the accuracy of the EM2010 system on Pride & Prejudice. This research was partially supported by the Natural Sciences and Engineering Research Council of Canada.