Probing Pretrained Language Models for Lexical Semantics
Ivan Vulić, Edoardo Maria Ponti, Robert Litschko, Goran Glavaš, Anna Korhonen
Abstract
The success of large pretrained language models (LMs) such as BERT and RoBERTa has sparked interest in probing their representations, in order to unveil what types of knowledge they implicitly capture. While prior research focused on morphosyntactic, semantic, and world knowledge, it remains unclear to which extent LMs also derive lexical type-level knowledge from words in context. In this work, we present a systematic empirical analysis across six typologically diverse languages and five different lexical tasks, addressing the following questions: 1) How do different lexical knowledge extraction strategies (monolingual versus multilingual source LM, out-of-context versus in-context encoding, inclusion of special tokens, and layer-wise averaging) impact performance? How consistent are the observed effects across tasks and languages? 2) Is lexical knowledge stored in few parameters, or is it scattered throughout the network? 3) How do these representations fare against traditional static word vectors in lexical tasks 4) Does the lexical information emerging from independently trained monolingual LMs display latent similarities? Our main results indicate patterns and best practices that hold universally, but also point to prominent variations across languages and tasks. Moreover, we validate the claim that lower Transformer layers carry more type-level lexical knowledge, but also show that this knowledge is distributed across multiple layers.- Anthology ID:
- 2020.emnlp-main.586
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7222–7240
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.586
- DOI:
- 10.18653/v1/2020.emnlp-main.586
- Cite (ACL):
- Ivan Vulić, Edoardo Maria Ponti, Robert Litschko, Goran Glavaš, and Anna Korhonen. 2020. Probing Pretrained Language Models for Lexical Semantics. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7222–7240, Online. Association for Computational Linguistics.
- Cite (Informal):
- Probing Pretrained Language Models for Lexical Semantics (Vulić et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.586.pdf
- Data
- United Nations Parallel Corpus