BRENT: Bidirectional Retrieval Enhanced Norwegian Transformer
This work provides the first retrieval-based model for Norwegian, addressing a gap in language-specific NLP tools, but it is incremental as it adapts an existing framework.
The researchers tackled the lack of Norwegian retrieval-based language models by adapting the REALM framework to create BRENT, showing that retrieval-augmented training improved the reader's performance on extractive question-answering without harming other linguistic tasks like part-of-speech tagging.
Retrieval-based language models are increasingly employed in question-answering tasks. These models search in a corpus of documents for relevant information instead of having all factual knowledge stored in its parameters, thereby enhancing efficiency, transparency, and adaptability. We develop the first Norwegian retrieval-based model by adapting the REALM framework and evaluating it on various tasks. After training, we also separate the language model, which we call the reader, from the retriever components, and show that this can be fine-tuned on a range of downstream tasks. Results show that retrieval augmented language modeling improves the reader's performance on extractive question-answering, suggesting that this type of training improves language models' general ability to use context and that this does not happen at the expense of other abilities such as part-of-speech tagging, dependency parsing, named entity recognition, and lemmatization. Code, trained models, and data are made publicly available.