Abstract
In this paper, we compare two different approaches to language understanding for a human-robot interaction domain in which a human commander gives navigation instructions to a robot. We contrast a relevance-based classifier with a GPT-2 model, using about 2000 input-output examples as training data. With this level of training data, the relevance-based model outperforms the GPT-2 based model 79% to 8%. We also present a taxonomy of types of errors made by each model, indicating that they have somewhat different strengths and weaknesses, so we also examine the potential for a combined model.- Anthology ID:
- 2022.lrec-1.625
- Volume:
- Proceedings of the Thirteenth Language Resources and Evaluation Conference
- Month:
- June
- Year:
- 2022
- Address:
- Marseille, France
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 5813–5820
- Language:
- URL:
- https://aclanthology.org/2022.lrec-1.625
- DOI:
- Cite (ACL):
- Ada Tur and David Traum. 2022. Comparing Approaches to Language Understanding for Human-Robot Dialogue: An Error Taxonomy and Analysis. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 5813–5820, Marseille, France. European Language Resources Association.
- Cite (Informal):
- Comparing Approaches to Language Understanding for Human-Robot Dialogue: An Error Taxonomy and Analysis (Tur & Traum, LREC 2022)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2022.lrec-1.625.pdf
- Data
- R2R