Casey Redd Kennington

Learn More
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(More)
This paper discusses development and evaluation of a practical, valid and reliable instrument for evaluating the spoken language abilities of second-language (L2) learners of English. First we sketch the theory and history behind elicited imitation (EI) tests and the renewed interest in them. Then we present how we developed a new test based on various(More)
We present work on understanding natural language in a situated domain, that is, language that possibly refers to visually present entities, in an incremental, word-by-word fashion. Such type of understanding is required in conversational systems that need to act immediately on language input, such as multi-modal systems or dialogue systems for robots. We(More)
A large part of human communication involves referring to entities in the world, and often these entities are objects that are visually present for the interlocutors. A computer system that aims to resolve such references needs to tackle a complex task: objects and their visual features must be determined, the referring expressions must be recognised,(More)
“You see a red building, and then behind that [gesture] you turn left”. Hearing this kind of route description, only to apply its instructions at a later time, is a difficult task. The content of the description has to be memorised, and then, when the time comes to make use of it, be applied to the present situation. This makes for a good test case for a(More)
When referring to visually-present objects, an elementary site of language use, sometimes there isn’t enough information to resolve the speaker’s intended object. When this happens, more information needs to be elicited from the speaker. In this demo, we will show a simple system that uses the word-as-classifiers model to resolve referring expressions to(More)
In situated dialogue, speakers share time and space. We present a statistical model for understanding natural language that works incrementally (i.e., in real, shared time) and is grounded (i.e., links to entities in the shared space). We describe our model with an example, then establish that our model works well on nonsituated, telephony application-type(More)