With raised eyebrows or the eyebrows raised ? A Neural Network Approach to Grammar Checking for Definiteness

In this paper, we use a feature model of the semantics of plural determiners to present an approach to grammar checking for definiteness. Using neural network techniques, a semantics – morphological category mapping was learned. We then applied a textual encoding technique to the 125 occurences of the relevant category in a 10 000 word narrative text and learned a surface – semantics mapping. By applying the learned generation function to the newly generated representations, we achieved a correct category assignment in many cases (87%). These results are considerably better than a direct surface categorization approach (54 %), with a baseline (always guessing the dominant category) of 60 %. It is discussed, how these results could be used in multilingual NLP applications.