Anaphora Resolution in Hindi

Nowadays machines have the ability of upturning the large matrices with speed and grace but they still fail to master the basics of the written and spoken languages to the machine. It is difficult to address computer as though addressing another person. So, there are various methods to resolve the problem of refereeing and this process is called anaphora resolution. Anaphora is very challenging job in Hindi language because the style of writing is changed with respect to the expressions. In this book, we have used hybrid approach which is the combination of rule based and learning based to resolve gender, number agreement, co-reference and animistic knowledge in Hindi domain. The results are computed by using various globally accepted evaluation metrics like MUC, B3, CEAF, F- score on three different data sets. The accuracy of the system is evaluated by kappa statistics.