Modeling Local Coherence: An Entity-Based Approach

This paper considers the problem of automatic assessment of local coherence. We present a novel entity-based representation of discourse which is inspired by Centering Theory and can be computed automatically from raw text. We view coherence assessment as a ranking learning problem and show that the proposed discourse representation supports the effective learning of a ranking function. Our experiments demonstrate that the induced model achieves significantly higher accuracy than a state-of-the-art coherence model.

• Type: Journal
• Year: 2008
• Where: COLING
• Authors: Regina Barzilay, Mirella Lapata
• Keywords: Coherence Assessment, COLING 2008, Computational Linguistics, Local Coherence, Ranking Learning Problem