Saara: Anaphora Resolution on Free Text in Czech
Václav Němčík · 2012
Anaphora resolution is one of the key parts of modern NLP systems, and not addressing it usually means a notable performance drop. Despite the abundance of theoretical studies published in the previous decades, real systems for resolving anaphora are rather rare. In this article we present, to our knowledge, the first practical anaphora resolution system applicable to Czech free text. We describe the individual stages of the processing pipeline and sketch the data format used as an interface between individual modules.