Feedback such as backchannels and clarification requests can occur subsententially, demonstrating the incremental nature of grounding in dialogue. However, although such feedback can occur at any point within an utterance, it typically does not do so, tending to occur at feedback relevance spaces (FRSs). We provide a low-level, semantic processing model of where feedback ought to be licensed. The model can account for cases where feedback occurs at FRSs, and how it can be integrated or interpreted at non-FRSs using the predictive, incremental and interactive nature of the formalism. This model shows how feedback serves to continually realign processing contexts and thus manage the characteristic divergence and convergence that is key to moving dialogue forward.
|Title of host publication||Proceedings of the 12th International Conference on Computational Semantics (IWCS)|
|Publisher||Association for Computational Linguistics|
|Publication status||Published - 19 Sep 2017|