NER of Citations and Fine-Grained Classification of Responsa.

Abstract

...However, responsa, especially those found online, are not neatly organized by topic. Thus, in order to take the analysis of responsa a step further and be able to garner information about the actual content of the questions being posed to rabbis, there has to be a way to split responsa into meaningful topics. The goal of this project was to write a program that would successfully split responsa into meaningful topics using Named Entity Recognition (NER). Before delving into the coding approach to the question at hand, the goal had to be better defined. What is considered a meaningful topic?