Probing Pretrained Language Models for Lexical Semantics
View / Open Files
Authors
Vulic, Ivan
Ponti, Edoardo
Litschko, Robert
Glavas, Goran
Korhonen, Anna
Journal Title
Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
Conference Name
Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
Publisher
Association for Computational Linguistics
Type
Conference Object
This Version
VoR
Metadata
Show full item recordCitation
Vulic, I., Ponti, E., Litschko, R., Glavas, G., & Korhonen, A. Probing Pretrained Language Models for Lexical Semantics. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2020) https://doi.org/10.18653/v1/2020.emnlp-main.586
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.
Sponsorship
ECH2020 EUROPEAN RESEARCH COUNCIL (ERC) (648909)
Identifiers
External DOI: https://doi.org/10.18653/v1/2020.emnlp-main.586
This record's URL: https://www.repository.cam.ac.uk/handle/1810/315105
Rights
All rights reserved