Character profiling in low-resource language documents

Abstract

This paper focuses on automatic character profiling — connecting “who”, “what” and “when” — in literary documents. This task is especially challenging for low-resource languages, since off-the-shelf tools for named entity recognition, syntactic parsing and other natural language processing tasks are rarely available. We investigate the impact of human annotation on automatic profiling. Based on a Medieval Chinese corpus, experimental results show that even a relatively small amount of word segmentation, part-of-speech and dependency annotation can improve accuracy in named entity recognition and in identifying character-verb associations, but not character-toponym associations.