Entity-Based Local Coherence Modelling Using Topological Fields

One goal of natural language generation is to produce coherent text that presents information in a logical order. In this paper, we show that topological fields, which model high-level clausal structure, are an important component of local coherence in German. First, we show in a sentence ordering experiment that topological field information improves the entity grid model of Barzilay and Lapata (2008) more than grammatical role and simple clausal order information do, particularly when manual annotations of this information are not available. Then, we incorporate the model enhanced with topological fields into a natural language generation system that generates constituent orders for German text, and show that the added coherence component improves performance slightly, though not statistically significantly.

• Type: Journal
• Year: 2010
• Where: ACL
• Authors: Jackie Chi Kit Cheung, Gerald Penn
• Keywords: ACL 2010, Computational Linguistics, Natural Language Generation, Topological Field Information, Topological Fields