Attention Understands Semantic Relations

Anastasia Chizhikova, Sanzhar Murzakhmetov, Oleg Serikov, Tatiana Shavrina, Mikhail Burtsev


Abstract
Today, natural language processing heavily relies on pre-trained large language models. Even though such models are criticized for the poor interpretability, they still yield state-of-the-art solutions for a wide set of very different tasks. While lots of probing studies have been conducted to measure the models’ awareness of grammatical knowledge, semantic probing is less popular. In this work, we introduce the probing pipeline to study the representedness of semantic relations in transformer language models. We show that in this task, attention scores are nearly as expressive as the layers’ output activations, despite their lesser ability to represent surface cues. This supports the hypothesis that attention mechanisms are focusing not only on the syntactic relational information but also on the semantic one.
Anthology ID:
2022.lrec-1.430
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
4040–4050
Language:
URL:
https://aclanthology.org/2022.lrec-1.430
DOI:
Bibkey:
Cite (ACL):
Anastasia Chizhikova, Sanzhar Murzakhmetov, Oleg Serikov, Tatiana Shavrina, and Mikhail Burtsev. 2022. Attention Understands Semantic Relations. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 4040–4050, Marseille, France. European Language Resources Association.
Cite (Informal):
Attention Understands Semantic Relations (Chizhikova et al., LREC 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lrec-1.430.pdf
Data
DocRED