تقرير
NeBuLa: A discourse aware Minecraft Builder
العنوان: | NeBuLa: A discourse aware Minecraft Builder |
---|---|
المؤلفون: | Chaturvedi, Akshay, Thompson, Kate, Asher, Nicholas |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Machine Learning |
الوصف: | When engaging in collaborative tasks, humans efficiently exploit the semantic structure of a conversation to optimize verbal and nonverbal interactions. But in recent "language to code" or "language to action" models, this information is lacking. We show how incorporating the prior discourse and nonlinguistic context of a conversation situated in a nonlinguistic environment can improve the "language to action" component of such interactions. We fine tune an LLM to predict actions based on prior context; our model, NeBuLa, doubles the net-action F1 score over the baseline on this task of Jayannavar et al.(2020). We also investigate our model's ability to construct shapes and understand location descriptions using a synthetic dataset. Comment: 10 pages, 3 figures |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2406.18164 |
رقم الأكسشن: | edsarx.2406.18164 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |