Toward interface design for human language technology: Modality and structure as determinants of linguistic complexity

Abstract

Before next-generation human language technology can be designed to function successfully in actual field settings, interface techniques will be needed that can guide users' language to coincide with current system capabilities. The present study examines how input modality and presentation structure influence the linguistic complexity observed in people's spoken and written input to an interactive system. Using a semi-automatic simulation technique, language was collected during speech-only, writing-only and combined pen/voice exchanges, and using presentation formats that either were structured or unconstrained. Results indicate that both modality and presentation format substantially influence linguistic complexity, although the specific nature of their impact differs. A comprehensive analysis is provided of how both factors affect people's observed language in terms of total words, disfluencies, utterance length, lexical variability, perplexity, syntactic ambiguity and semantic integration. Users' preferences for modalities and formats also are analyzed, and implications are discussed for channeling people's language in a transparent way. The long-term goal of this research is to develop interface techniques for managing difficult sources of variability in people's language, so that robust processing of human language technology can be achieved.