Modeling Local Coherence: An Entity-Based Approach

Modeling Local Coherence: An Entity-Based Approach Regina Barzilay∗ Massachusetts Institute of Technology Mirella Lapata∗∗ University of Edinburgh This article proposes a novel framework for representing and measuring local coherence. Central to this approach is the entity-grid representation of discourse, which captures patterns of entity distribution in a text. The algorithm introduced in the article automatically abstracts a text into a set of entity transition sequences and records distributional, syntactic, and referential information about discourse entities. We re-conceptualize coherence assessment as a learning task and show that our entity-based representation is well-suited for ranking-based generation and text classification tasks. Using the proposed representation, we achieve good performance on text ordering, summary coherence evaluation, and readability assessment. 1. Introduction A key requirement for any system that produces text is the coherence of its output. Not surprisingly, a variety of coherence theories have been developed over the years (e.g., Mann and Thomson 1988; Grosz et al. 1995) and their principles have found application in many symbolic text generation systems (e.g., Scott and de Souza 1990; Kibble and Power 2004). The ability of these systems to generate high quality text, almost indistinguishable from human writing, makes the incorporation of coherence theories in robust large-scale systems particularly appealing. The task is, however, challenging considering that most previous efforts have relied on handcrafted rules, valid only for limited domains, with no guarantee of scalability or portability (Reiter and Dale 2000). Furthermore, coherence constraints are often embedded in complex representations (e.g., Asher and Lascarides 2003) which are hard to implement in a robust application. This article focuses on local coherence, which captures text relatedness at the level of sentence-to-sentence transitions. Local coherence is undoubtedly necessary for global coherence and has received considerable attention in computational linguistics (Foltz, Kintsch, and Landauer 1998; Marcu 2000; Lapata 2003; Althaus, Karamanis, and Koller ∗ Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, 32-G468 Cambridge, MA 02139. E-mail: regina@csail.mit.edu. ∗∗ School of Informatics, University of Edinburgh, EH8 9LW, Edinburgh, UK. E-mail: mlap@inf.ed.ac.uk. Submission received: 29 November 2005; revised submission received: 6 March 2007; accepted for publication: 5 May 2007. © 2008 Association for Computational Linguistics Computational Linguistics Volume 34, Number 1 2004; Karamanis et al. 2004). It is also supported by much psycholinguistic evidence. For instance, McKoon and Ratcliff (1992) argue that local coherence is the primary source of inference-making during reading. The key premise of our work is that the distribution of entities in locally coher- ent texts exhibits certain regularities. This assumption is not arbitrary—some of these regularities have been recognized in Centering Theory (Grosz, Joshi, and Weinstein 1995) and other entity-based theories of discourse (e.g., Givon 1987; Prince 1981). The algorithm introduced in the article automatically abstracts a text into a set of entity tran- sition sequences, a representation that reflects distributional, syntactic, and referential information about discourse entities. We argue that the proposed entity-based representation of discourse allows us to learn the properties of coherent texts from a corpus, without recourse to manual …

Content truncated to 500 words