Modelling and Evaluation of Lexical and Syntactic Alignment with a Priming-Based Microplanner

Abstract

Abstract. Alignment of interlocutors is a well known psycholinguistic phenomenon of great relevance for dialogue systems in general and natural language generation in particular. In this chapter, we present the alignment-capable microplanner SPUD prime. Using a priming-based model of interactive alignment, it is flexible enough to model the alignment behaviour of human speakers to a high degree. We demonstrate that SPUD prime can account for lexical as well as syntactic alignment and present an evaluation on corpora of task-oriented dialogue that were collected in two experiments designed to investigate the alignment behaviour of humans in a controlled fashion. This will allow for further investigation of which parameters are important to model alignment and how the human-computer interaction changes when the computer aligns to its users.

Automatic Measures to Characterise Verbal Alignment in Human-Agent Interaction

“…the tendency to use the same terms when DPs refer repeatedly to the same objects (Brennan and Clark, 1996). Several entrainment models have been proposed to let the system entrains to user utterances (e.g., (Brockmann et al, 2005;Buschmeier et al, 2010;Hu et al, 2014;Lopes et al, 2015)). These models are completely or partially rule-based and focus on specific aspects of entrainment.…”

A Context-aware Natural Language Generator for Dialogue Systems

“…There have been several attempts at modelling entrainment in dialogue (Brockmann et al, 2005;Reitter et al, 2006;Buschmeier et al, 2010) and even successful implementations of entrainment models in NLG systems for SDS, where entrainment caused an increase in perceived naturalness of the system responses (Hu et al, 2014) or increased naturalness and task success (Lopes et al, 2013; Lopes et al, 2015). However, all of the previous approaches are completely or partially rulebased.…”

Toward a Computational Psycholinguistics of Reference Production

“…Many authors see alignment as the result of a mechanistic, largely automatic process where speakers produce expressions that are easy to comprehend for their addressee because they rely on representations that were used (‘‘primed’’) earlier on in the interaction. We do not know of any attempts to model the priming mechanisms outlined by Pickering and Garrod in computational reg , though they may be discerned in other subtasks of Natural Language Generation (e.g., Buschmeier, Bergmann, & Kopp, 2010; Purver & Kempson, 2004).…”