A fundamental requirement of any task-oriented dialogue system is the ability to generate object descriptions that refer to objects in the task domain. The subproblem of content selection for object descriptions in task-oriented dialogue has been the focus of much previous work and a large number of models have been proposed. In this paper, we use the annotated coconut corpus of task-oriented design dialogues to develop feature sets based on Dale and Reiter’s (1995) incremental model, Brennan and Clark’s (1996) conceptual pact model, and Jordan’s (2000b) intentional influences model, and use these feature sets in a machine learning experiment to automatically learn a model of content selection for object descriptions. Since Dale and Reiter’s model requires a representation of discourse structure, the corpus annotations are used to derive a representation based on Grosz and Sidner’s (1986) theory of the intentional structure of discourse, as well as two very simple representations of discourse structure based purely on recency. We then apply the rule-induction program ripper to train and test the content selection component of an object description generator on a set of 393 object descriptions from the corpus. To our

It would be useful to enable dialogue agents to project, through linguistic means, their individuality or personality. Equally, each member of a pair of agents ought to adjust its language (to a greater or lesser extent) to match that of its interlocutor. We describe CRAG, which generates dialogues between pairs of agents, who are linguistically distinguishable, but able to align. CRAG-2 makes use of OPENCCG and an over-generation and ranking approach, guided by a set of language models covering both personality and alignment. We illustrate with examples of output, and briefly note results from user studies with the earlier CRAG-1, indicating how CRAG-2 will be further evaluated. Related work is discussed, along with current limitations and future directions.

Experimental research in psycholinguistics has demonstrated a parallelism effect in coordination: speakers are faster at processing the second conjunct of a coordinate structure if it has the same internal structure as the first conjunct. We show that this phenomenon can be explained by the prevalence of parallel structures in corpus data. We demonstrate that parallelism is not limited to coordination, but also applies to arbitrary syntactic configurations, and even to documents. This indicates that the parallelism effect is an instance of a general syntactic priming mechanism in human language processing. 1

The emergence of human communication systems is typically investigated via 2 approaches with complementary strengths and weaknesses: naturalistic studies and computer simulations. This study was conducted with a method that combines these approaches. Pairs of participants played video games requiring communication. Members of a pair were physically separated but exchanged graphic signals through a medium that prevented the use of standard symbols (e.g., letters). Communication systems emerged and developed rapidly during the games, integrating the use of explicit signs with information implicitly available to players and silent behavior-coordinating procedures. The systems that emerged suggest 3 conclusions: (a) signs originate from different mappings; (b) sign systems develop parsimoniously; (c) sign forms are perceptually distinct, easy to produce, and tolerant to variations.

1 Language in the World How does language relate to the non-linguistic world? If an agent is able to communicate linguistically and is also able to directly perceive and/or act on the world, how do perception, action, and language interact with and influence each other? Such questions are surely amongst the most important in Cognitive Science and Artificial Intelligence (AI). Language, after all, is a central aspect of the human mind – indeed it may be what distinguishes us from other species. There is sometimes a tendency in the academic world to study language in isolation, as a formal system with rules for well-constructed sentences; or to focus on how language relates to formal notations such as symbolic logic. But language did not evolve as an isolated system or as a way of communicating symbolic logic; it presumably evolved as a mechanism for exchanging information about the world, ultimately providing the medium for cultural transmission across generations. Motivated by these observations, the goal of this special issue is to bring together research in AI that focuses on relating language to the physical world. Language is of course also used to communicate about non-physical referents, but the ubiquity of physical metaphor in language [21] suggests that grounding in the physical world provides the foundations of semantics.

Syntactic priming effects, modelled as increase in repetition probability shortly after a use of a syntactic rule, have the potential to improve language processing components. We model priming of syntactic rules in annotated corpora of spoken dialogue, extending previous work that was confined to selected constructions. We find that speakers are more receptive to priming from their interlocutor in task-oriented dialogue than in sponaneous conversation. Low-frequency rules are more likely to show priming. 1

Clarification requests are an important, relatively common and yet under-studied dialogue device allowing a user to ask about some feature (e.g. the meaning or form) of an utterance, or part thereof. They can take many different forms (often highly elliptical) and can have many different meanings (requesting various types of information). This thesis combines empirical, theoretical and implementational work to provide a study of the various types of clarification request that exist, give a theoretical analysis thereof, and show how the results can be applied to add useful capabilities to a prototype computational dialogue system. A series

Standard grammar formalisms are defined without reflection of the incremental, serial and context-dependent nature of language processing; any incrementality must therefore be reflected by independently defined parsing and/or generation techniques, and context-dependence by separate pragmatic modules. This leads to a poor setup for modelling dialogue, with its rich speaker-hearer interaction and high proportion of context-dependent and apparently grammatically ill-formed utterances. Instead, this paper takes an inherently incremental grammar formalism (Dynamic Syntax: Kempson et al., 2001), proposes a context-based extension and defines corresponding contextdependent parsing and generation models together with a resulting natural definition of context-dependent well-formedness. These are shown to allow a straightforward model of otherwise problematic dialogue phenomena such as shared utterances, ellipsis and alignment. We conclude that language competence is a capacity for dialogue. 1

For a successful and satisfying interaction, a dialogue participant may align their language to be more like that of their interlocutor. In the first part of this paper, we examine the alignment phenomenon from the viewpoint of personalityrelated, linguistic, sociolinguistic and psycholinguistic research, concluding that some people are stronger aligners than others. Motivated by these results, we describe an approach to modelling alignment behaviour in a natural language generation system, using the OpenCCG surface realiser [30], which allows utterance candidates to be ranked by n-gram language models. We investigate the extent to which alignment can be simulated using word sequences alone (not syntactic structures). To this end, we interpolate a default language model with one calculated on the basis of a cached sentence. Experiments on sentences with the prepositional/double object alternation show that varying the weight given to the cache model varies the propensity to align. 1.

in human-robot interaction