Finding Voices in the Margins: Computer-Assisted Discovery of Naturally Belonging Names

• In Event: Advances in Text Analysis Methods

Abstract

We consider the problem of finding persons in a particular role within a large corpus. We propose a method for automatically generating suggestions of names found in the corpus which “naturally” belong to a given initial list of members. The approach is based, in part, on the assumption that surface level syntactic features reveal parts of the underlying semantic content. We argue that this is an efficient heuristic.

Authors

• Truls Pedersen, U of Bergen

• Samia Touileb, U of Bergen

• Helle Sjovaag, University of Stavanger