A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting

Pradyumna Tambwekar, Lakshita Dodeja, Nathan Vaska, Wei Xu, Matthew Gombolay

Abstract
Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling humans to specify, through language, exactly how an agent should complete a task (i.e., low-level specification), prior work lacks on interpreting the high-level strategic intent of the human commanders. Parsing strategic intent from language will allow autonomous systems to independently operate according to the user’s plan without frequent guidance or instruction. In this paper, we build a computational interface capable of translating unstructured language strategies into actionable intent in the form of goals and constraints. Leveraging a game environment, we collect a dataset of over 1000 examples, mapping language strategies to the corresponding goals and constraints, and show that our model, trained on this dataset, significantly outperforms human interpreters in inferring strategic intent (i.e., goals and constraints) from language (p < 0.05). Furthermore, we show that our model (125M parameters) significantly outperforms ChatGPT for this task (p < 0.05) in a low-data setting.
Anthology ID:
2023.findings-emnlp.853
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12801–12819
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.853
DOI:
10.18653/v1/2023.findings-emnlp.853
Bibkey:
Cite (ACL):
Pradyumna Tambwekar, Lakshita Dodeja, Nathan Vaska, Wei Xu, and Matthew Gombolay. 2023. A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12801–12819, Singapore. Association for Computational Linguistics.
Cite (Informal):
A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting (Tambwekar et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-emnlp.853.pdf
PDF Search