Contextually–Mediated Semantic Similarity Graphs for Topic Segmentation
Geetu Ambwani, Anthony R. Davis · 2013
We present a representation of documents as directed, weighted graphs, modeling the range of influence of terms within the document as well as contextually determined semantic relatedness among terms. We then show the usefulness of this kind of representation in topic segmentation. Our boundary detection algorithm uses this graph to determine topical coherence and potential topic shifts, and does not require labeled data or training of parameters. We show that this method yields improved results on both concatenated pseudo-documents and on closed-captions for television programs. 1