| identifying anaphoric and non-anaphoric noun phrases to improve coreference resolution we present a supervised learning approach o identification of anaphoric and non-anaphoric noun phrases and how how such information can be incorporated into a coreference resolution system. the resulting system outperforms the best muc-6 and muc-7 coreference resolution systems on the corresponding muc coreference data sets, obtaining f-measures of 66.2 and 64.0, respectively. we train a separate anaphoricity classifier in addition to a coreference model. we challenge the motivation for the inclusion of such detectors, reporting no improvements, or even worse performance. |