{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-to-generate-and-corr-uh-i-mean","title":"Learning to generate and corr- uh I mean repair language in real-time","arxiv_id":"2308.11683","date":"2023-08-22","proceeding":null,"authors":["Arash Eshghi","Arash Ashrafzadeh"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2308.11683v1","url_pdf":"https://arxiv.org/pdf/2308.11683v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-to-generate-and-corr-uh-i-mean","repo_url":"https://bitbucket.org/dylandialoguesystem/dsttr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"repair","method_name":"Repair"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.11683","atlas_url":"https://app.syntology.ai/?focus=2308.11683","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}