Processing Self-Repairs in an Incremental Type-Theoretic Dialogue System
نویسندگان
چکیده
We present a novel incremental approach to modelling self-repair phenomena in dialogue, using the grammar and parsing mechanism of Dynamic Syntax (DS) to construct Type Theory with Records (TTR) record type representations incrementally in both parsing and generation. We demonstrate how a DS-TTR hybrid implementation when integrated into an incremental dialogue system can be exploited to account for the semantic processing of selfrepair phenomena in a unified way and in line with psycholinguistic evidence.
منابع مشابه
Modelling incremental self-repair processing in dialogue
Self-repairs, where speakers repeat themselves, reformulate or restart what they are saying, are pervasive in human dialogue. These phenomena provide a window into real-time human language processing. For explanatory adequacy, a model of dialogue must include mechanisms that account for them. Artificial dialogue agents also need this capability for more natural interaction with human users. Thi...
متن کاملIncremental Semantics Driven Natural Language Generation with Self-Repairing Capability
This paper presents the on-going development of a model of incremental semantics driven natural language generation (NLG) for incremental dialogue systems. The approach is novel in its tight integration of incremental goal-driven semantics and syntactic construction, utilizing Type Theory with Records (TTR) record types for goal concepts as its input and the grammar formalism Dynamic Syntax (DS...
متن کاملModelling Expectation in the Self-Repair Processing of Annotat-, um, Listeners
This paper describes a statistical corpus study of self-repairs in the disfluencyannotated Switchboard corpus which examines the time-linear nature of self-repair processing for annotators and listeners in dialogue. The study suggests a strictly local detection and processing mechanism for self-repairs is sufficient, an advantage currently not used effectively under the bonnet of state-of-the-a...
متن کاملProbabilistic Record Type Lattices for Incremental Reference Processing
This chapter addresses the issue of incorporating probabilistic type-theoretic inference into an incremental dialogue framework, using processing of referring expressions (that is, their interpretation and generation) as a test case. Within our framework, we model reference processing in a psycholinguistically plausible way– that is, in a strictly left-to-right, word-by-word, incremental fashio...
متن کاملProbabilistic Type Theory for Incremental Dialogue Processing
We present an adaptation of recent work on probabilistic Type Theory with Records (Cooper et al., 2014) for the purposes of modelling the incremental semantic processing of dialogue participants. After presenting the formalism and dialogue framework, we show how probabilistic TTR type judgements can be integrated into the inference system of an incremental dialogue system, and discuss how this ...
متن کامل