Litcius/Paper detail

Go Simple and Pre-Train on Domain-Specific Corpora: On the Role of Training Data for Text Classification

Aleksandra Edwards, José Camacho-Collados, Hélène de Ribaupierre, Alun Preece

202025 citationsDOIOpen Access PDF

Abstract

Pre-trained language models provide the foundations for state-of-the-art performance across a wide range of natural language processing tasks, including text classification. However, most classification datasets assume a large amount labeled data, which is commonly not the case in practical settings. In particular, in this paper we compare the performance of a light-weight linear classifier based on word embeddings, i.e., fastText In general, results show the importance of domain-specific unlabeled data, both in the form of word embeddings or language models. As for the comparison, BERT outperforms all baselines in standard datasets with large training sets. However, in settings with small training datasets a simple method like fastText coupled with domain-specific word embeddings performs equally well or better than BERT, even when pre-trained on domain-specific data.

Topics & Concepts

Computer scienceSimple (philosophy)Training (meteorology)Training setDomain (mathematical analysis)Natural language processingArtificial intelligenceInformation retrievalPhysicsEpistemologyMeteorologyMathematicsMathematical analysisPhilosophyNatural Language Processing TechniquesTopic ModelingText and Document Classification Technologies