BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?

Asahi Ushio, Luis Espinosa Anke, Steven Schockaert, Jose Camacho-Collados


Abstract
Analogies play a central role in human commonsense reasoning. The ability to recognize analogies such as “eye is to seeing what ear is to hearing”, sometimes referred to as analogical proportions, shape how we structure knowledge and understand language. Surprisingly, however, the task of identifying such analogies has not yet received much attention in the language model era. In this paper, we analyze the capabilities of transformer-based language models on this unsupervised task, using benchmarks obtained from educational settings, as well as more commonly used datasets. We find that off-the-shelf language models can identify analogies to a certain extent, but struggle with abstract and complex relations, and results are highly sensitive to model architecture and hyperparameters. Overall the best results were obtained with GPT-2 and RoBERTa, while configurations using BERT were not able to outperform word embedding models. Our results raise important questions for future work about how, and to what extent, pre-trained language models capture knowledge about abstract semantic relations.
Anthology ID:
2021.acl-long.280
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3609–3624
Language:
URL:
https://aclanthology.org/2021.acl-long.280
DOI:
10.18653/v1/2021.acl-long.280
Bibkey:
Cite (ACL):
Asahi Ushio, Luis Espinosa Anke, Steven Schockaert, and Jose Camacho-Collados. 2021. BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3609–3624, Online. Association for Computational Linguistics.
Cite (Informal):
BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies? (Ushio et al., ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.280.pdf
Code
 asahi417/analogy-language-model
Data
Analogy Test