Can BERT Dig It? -- Named Entity Recognition for Information Retrieval in the Archaeology Domain

TL;DR

This paper introduces ArcheoBERTje, a domain-specific BERT model for archaeological NER, demonstrating significant performance improvements over generic models and showing that domain-specific pre-training reduces the need for additional domain knowledge integration.

Contribution

The paper presents ArcheoBERTje, a BERT model pre-trained on Dutch archaeological texts, and compares its NER performance to generic models, highlighting the benefits of domain-specific pre-training.

Findings

ArcheoBERTje outperforms generic models with an F1 score of 0.735.

Domain-specific pre-training significantly improves NER quality.

Adding domain knowledge from a thesaurus does not enhance model performance.

Abstract

The amount of archaeological literature is growing rapidly. Until recently, these data were only accessible through metadata search. We implemented a text retrieval engine for a large archaeological text collection ($\sim 658$ Million words). In archaeological IR, domain-specific entities such as locations, time periods, and artefacts, play a central role. This motivated the development of a named entity recognition (NER) model to annotate the full collection with archaeological named entities. In this paper, we present ArcheoBERTje, a BERT model pre-trained on Dutch archaeological texts. We compare the model's quality and output on a Named Entity Recognition task to a generic multilingual model and a generic Dutch model. We also investigate ensemble methods for combining multiple BERT models, and combining the best BERT model with a domain thesaurus using Conditional Random Fields (CRF). We find that ArcheoBERTje outperforms both the multilingual and Dutch model significantly with a smaller standard deviation between runs, reaching an average F1 score of 0.735. The model also outperforms ensemble methods combining the three models. Combining ArcheoBERTje predictions and explicit domain knowledge from the thesaurus did not increase the F1 score. We quantitatively and qualitatively analyse the differences between the vocabulary and output of the BERT models on the full collection and provide some valuable insights in the effect of fine-tuning for specific domains. Our results indicate that for a highly specific text domain such as archaeology, further pre-training on domain-specific data increases the model's quality on NER by a much larger margin than shown for other domains in the literature, and that domain-specific pre-training makes the addition of domain knowledge from a thesaurus unnecessary.