Summary of Nebula: a Discourse Aware Minecraft Builder, by Akshay Chaturvedi et al.
Nebula: A discourse aware Minecraft Builder
by Akshay Chaturvedi, Kate Thompson, Nicholas Asher
First submitted to arxiv on: 26 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a novel approach to improving “language to code” or “language to action” models by incorporating the prior discourse and nonlinguistic context of a conversation. The authors demonstrate how this contextual information can enhance the performance of these models, specifically showing that their finetuned large language model (LLM), called Nebula, doubles the net-action F1 score compared to a baseline on a task similar to Jayannavar et al.’s work from 2020. Additionally, the paper explores Nebula’s ability to construct shapes and understand location descriptions using a synthetic dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps computers better understand conversations by considering what happened before in the conversation. The authors show that if we include this prior context, our computer models can make better predictions about what will happen next. They test their new approach on a specific task and find it works really well. They also try using their model to build shapes and understand location descriptions. |
Keywords
» Artificial intelligence » Discourse » F1 score » Large language model
