ProSPer: Probing Human and Neural Network Language Model Understanding of Spatial Perspective

Tessa Masis, Carolyn Anderson


Abstract
Understanding perspectival language is important for applications like dialogue systems and human-robot interaction. We propose a probe task that explores how well language models understand spatial perspective. We present a dataset for evaluating perspective inference in English, ProSPer, and use it to explore how humans and Transformer-based language models infer perspective. Although the best bidirectional model performs similarly to humans, they display different strengths: humans outperform neural networks in conversational contexts, while RoBERTa excels at written genres.
Anthology ID:
2021.blackboxnlp-1.8
Volume:
Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Jasmijn Bastings, Yonatan Belinkov, Emmanuel Dupoux, Mario Giulianelli, Dieuwke Hupkes, Yuval Pinter, Hassan Sajjad
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
95–135
Language:
URL:
https://aclanthology.org/2021.blackboxnlp-1.8
DOI:
10.18653/v1/2021.blackboxnlp-1.8
Bibkey:
Cite (ACL):
Tessa Masis and Carolyn Anderson. 2021. ProSPer: Probing Human and Neural Network Language Model Understanding of Spatial Perspective. In Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 95–135, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
ProSPer: Probing Human and Neural Network Language Model Understanding of Spatial Perspective (Masis & Anderson, BlackboxNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.blackboxnlp-1.8.pdf
Code
 canders1/prosper