We present a general model and conceptual framework for specifying architectures for incremental processing in dialogue systems, in particular with respect to the topology of the network of modules that make up the system, the way information flows through this network, how information increments are 'packaged', and how these increments are processed by the modules. This model enables the precise specification of incremental systems and hence facilitates detailed comparisons between systems, as well as giving guidance on designing new systems.
An elementary way of using language is to refer to objects. Often, these objects are physically present in the shared environment and reference is done via mention of perceivable properties of the objects. This is a type of language use that is modelled well neither by logical semantics nor by distributional semantics, the former focusing on inferential relations between expressed propositions, the latter on similarity relations between words or phrases. We present an account of word and phrase meaning that is perceptually grounded, trainable, compositional, and 'dialogueplausible' in that it computes meanings word-by-word. We show that the approach performs well (with an accuracy of 65% on a 1-out-of-32 reference resolution task) on direct descriptions and target/landmark descriptions, even when trained with less than 800 training examples and automatically transcribed utterances.
This paper describes a fully incremental dialogue system that can engage in dialogues in a simple domain, number dictation. Because it uses incremental speech recognition and prosodic analysis, the system can give rapid feedback as the user is speaking, with a very short latency of around 200ms. Because it uses incremental speech synthesis and self-monitoring, the system can react to feedback from the user as the system is speaking. A comparative evaluation shows that naïve users preferred this system over a non-incremental version, and that it was perceived as more human-like.
1 The code for reproducing the results reported in this paper can be found at https://github.com/ dsg-bielefeld/image_wac.
CodeThe code required for reproducing the results reported here can be found at https://github.com/dsg-bielefeld/ image_wac.
Research on generating referring expressions has so far mostly focussed on "oneshot reference", where the aim is to generate a single, discriminating expression. In interactive settings, however, it is not uncommon for reference to be established in "installments", where referring information is offered piecewise until success has been confirmed. We show that this strategy can also be advantageous in technical systems that only have uncertain access to object attributes and categories. We train a recently introduced model of grounded word meaning on a data set of REs for objects in images and learn to predict semantically appropriate expressions. In a human evaluation, we observe that users are sensitive to inadequate object names -which unfortunately are not unlikely to be generated from low-level visual input. We propose a solution inspired from human task-oriented interaction and implement strategies for avoiding and repairing semantically inaccurate words. We enhance a word-based REG with contextaware, referential installments and find that they substantially improve the referential success of the system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.