Let's get into it: using contextualized embeddings as retrieval tools

Fonteyn, L.

doi:doi:10.1075/bjl.00035.fon

This squib briefly explores how contextualized embeddings – which are a type of compressed token-based semantic vectors – can be used as semantic retrieval and annotation tools for corpus-based research into constructions. Focusing on embeddings created by the Bidirectional Encoder Representations from Transformer model, also known as ‘BERT’, this squib demonstrates how contextualized embeddings can help counter two types of retrieval inefficiency scenarios that may arise with purely form-based corpus queries. In the first scenario, the formal query yields a large number of hits, which contain a reasonable number of relevant examples that can be labeled and used as input for a sense disambiguation classifier. In the second scenario, the contextualized embeddings of exemplary tokens are used to retrieve more relevant examples in a large, unlabeled dataset. As a case study, this squib focuses on the INTO-INTEREST...Show moreThis squib briefly explores how contextualized embeddings – which are a type of compressed token-based semantic vectors – can be used as semantic retrieval and annotation tools for corpus-based research into constructions. Focusing on embeddings created by the Bidirectional Encoder Representations from Transformer model, also known as ‘BERT’, this squib demonstrates how contextualized embeddings can help counter two types of retrieval inefficiency scenarios that may arise with purely form-based corpus queries. In the first scenario, the formal query yields a large number of hits, which contain a reasonable number of relevant examples that can be labeled and used as input for a sense disambiguation classifier. In the second scenario, the contextualized embeddings of exemplary tokens are used to retrieve more relevant examples in a large, unlabeled dataset. As a case study, this squib focuses on the INTO-INTEREST construction (e.g. I’m so into you).
Show less

Leiden University Scholarly Publications

View statistics

Documents

In Collections

Let's get into it: using contextualized embeddings as retrieval tools