Interactive Grounded Language Understanding in a Collaborative Environment: Retrospective on Iglu 2022 Competition
| Authors |
|
|---|---|
| Publication date | 2023 |
| Journal | Proceedings of Machine Learning Research |
| Event | Thirty-sixth Conference on Neural Information Processing Systems |
| Volume | Issue number | 220 |
| Pages (from-to) | 204-216 |
| Organisations |
|
| Abstract |
Human intelligence possesses the extraordinary ability to adapt rapidly to new tasks and multi-modal environments. This capacity emerges at an early age, as humans acquire new skills and learn to solve problems by imitating others or following natural language instructions. To facilitate research in this area, we recently hosted the second \emph{IGLU: Interactive Grounded Language Understanding in a Collaborative Environment} competition. The primary objective of the competition is to address the challenge of creating interactive agents that can learn to solve complex tasks by receiving grounded natural language instructions in a collaborative environment. Given the complexity of this challenge, we divided it into two sub-tasks: first, deciding whether the provided grounded instruction requires clarification, and second, following a clear grounded instruction to complete the task description.
|
| Document type | Article |
| Note | Proceedings of the NeurIPS 2022 Competitions Track , 28-9 December 2022, New Orleans, LA, Online |
| Language | English |
| Published at | https://doi.org/10.48550/arXiv.2205.13771 |
| Published at | https://proceedings.mlr.press/v220/kiseleva23a.html |
| Downloads |
2205.13771v1
(Submitted manuscript)
kiseleva23a
(Final published version)
|
| Permalink to this page | |
