Recent work has shown that explicitly identifying and filtering non-anaphoric mentions prior to coreference resolution can improve the performance of a coreference system. We present a novel approach to this task of anaphoricity determination based on graph cuts, and demonstrate its superiority to competing approaches by comparing their effectiveness in improving a learning-based coreference sy...

Instance sampling is a method to balance extremely skewed training sets as they occur, for example, in machine learning settings for anaphora resolution. Here, the number of negative samples (i.e. non-anaphoric pairs) is usually substantially larger than the number of positive samples. This causes classifiers to be biased towards negative classification, leading to subopti-

This paper addresses the question whether possible alternative constructions and alternative choices of referring expressions influence the resolution of anaphoric expressions. We present a questionnaire, a self-paced reading study and a corpus analysis, suggesting that alternative constructions and referring expressions help to constitute preferences for anaphora in referentially ambiguous sen...

Information retrieval from music related text is an integral part of Music Information Retrieval(MIR) augmenting content based MIR. Discussion forums on music are rich sources of information gathered from a wider audience. There are a few music forums related to Indian classical music having notable information pertaining to entities including artiste, music concepts including raga, location et...

This paper presents a knowledge-poor method for the solution of anaphoric and deictic expressions in Dutch texts. The method is developed for use in a text summarization system. Anaphora resolution plays an important role in the analysis of the original text as well as in the generation of the text summary.

This paper reports our investigation of machine learning methods applied to anaphora resolution for Biology texts. Our primary concern is the investigation of features and their combinations for effective anaphora resolution. In this paper, we focus on the resolution of demonstrative anaphoric noun phrases. We propose several novel features that we call highlighting features and consider their ...

The long-term goal of this project is to build an annotated corpus of biomedical text, to be used as a foundation for the development of automated anaphora resolution systems. We plan to explore the feasibility of using a community of volunteers to annotate a corpus drawn from publically available biomedical literature. We present issues in creating such a community and discuss results obtained...

In this paper, effective Chinese definite anaphora resolution is addressed by using feature weight learning and Web-based knowledge acquisition. The presented salience measurement is based on entropybased weighting on selecting antecedent candidates. The knowledge acquisition model is aimed to extract more semantic features, such as gender, number, and semantic compatibility by employing multip...

The need for associating, or grounding, protein names in the literature with the entries of proteome databases such as Swiss-Prot is well-recognized. The protein names in the biomedical literature show a high degree of morphological and syntactic variations, and various anaphoric expressions including null anaphors. We present a biomedical anaphora resolution system, BioAR, in order to address ...