Learning to generate and corr- uh I mean repair language in real-time
This work addresses the need for fluent and natural conversational AI by enabling incremental language processing and self-repair, though it is incremental as it builds on existing grammar-based models.
The paper tackled the problem of real-time language generation and self-repair in conversational AI by developing a probabilistic model based on a Dynamic Syntax grammar and the CHILDES corpus, achieving 78% exact match for generation and 85% correct self-repairs in zero-shot evaluation.
In conversation, speakers produce language incrementally, word by word, while continuously monitoring the appropriateness of their own contribution in the dynamically unfolding context of the conversation; and this often leads them to repair their own utterance on the fly. This real-time language processing capacity is furthermore crucial to the development of fluent and natural conversational AI. In this paper, we use a previously learned Dynamic Syntax grammar and the CHILDES corpus to develop, train and evaluate a probabilistic model for incremental generation where input to the model is a purely semantic generation goal concept in Type Theory with Records (TTR). We show that the model's output exactly matches the gold candidate in 78% of cases with a ROUGE-l score of 0.86. We further do a zero-shot evaluation of the ability of the same model to generate self-repairs when the generation goal changes mid-utterance. Automatic evaluation shows that the model can generate self-repairs correctly in 85% of cases. A small human evaluation confirms the naturalness and grammaticality of the generated self-repairs. Overall, these results further highlight the generalisation power of grammar-based models and lay the foundations for more controllable, and naturally interactive conversational AI systems.