Probing Pretrained Language Models for Lexical Semantics

TL;DR

This paper systematically investigates how pretrained language models encode lexical semantics across diverse languages and tasks, revealing patterns, best practices, and the distribution of lexical knowledge within the models.

Contribution

It provides a comprehensive empirical analysis of lexical knowledge extraction strategies and compares their effectiveness across languages and tasks, highlighting the distribution of lexical information in models.

Findings

Lower Transformer layers contain more lexical knowledge.

Lexical knowledge is distributed across multiple layers.

Best practices vary across languages and tasks.

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.