Sudarshan Rangarajan

Learn More
Most coreference resolution models determine if two mentions are coreferent using a single function over a set of constraints or features. This approach can lead to incorrect decisions as lower precision features often overwhelm the smaller number of high precision ones. To overcome this problem, we propose a simple coreference architecture based on a sieve(More)
Effective Coreference Resolution is a must-have utility within many NLP pipelines. Machine translation , Text summarization, Parsing, Question answering are just a few NLP applications where such a utility provides the necessary confidence towards any decision of and within the system. In this project, we have implemented and investigated numerous(More)
  • 1