DeepAI AI Chat
Log In Sign Up

The merits of Universal Language Model Fine-tuning for Small Datasets – a case with Dutch book reviews

by   Benjamin van der Burgh, et al.
universiteit leiden

We evaluated the effectiveness of using language models, that were pre-trained in one domain, as the basis for a classification model in another domain: Dutch book reviews. Pre-trained language models have opened up new possibilities for classification tasks with limited labelled data, because representation can be learned in an unsupervised fashion. In our experiments we have studied the effects of training set size (100-1600 items) on the prediction accuracy of a ULMFiT classifier, based on a language models that we pre-trained on the Dutch Wikipedia. We also compared ULMFiT to Support Vector Machines, which is traditionally considered suitable for small collections. We found that ULMFiT outperforms SVM for all training set sizes and that satisfactory results ( 90 manually annotated within a few hours. We deliver both our new benchmark collection of Dutch book reviews for sentiment classification as well as the pre-trained Dutch language model to the community.


page 1

page 2

page 3

page 4


The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models

In this paper, we explore the effects of language variants, data sizes, ...

Is word segmentation necessary for Vietnamese sentiment classification?

To the best of our knowledge, this paper made the first attempt to answe...

Prompt Algebra for Task Composition

We investigate whether prompts learned independently for different tasks...

Evaluating the Effectiveness of Pre-trained Language Models in Predicting the Helpfulness of Online Product Reviews

Businesses and customers can gain valuable information from product revi...

Exploring Lottery Prompts for Pre-trained Language Models

Consistently scaling pre-trained language models (PLMs) imposes substant...

Probing Task-Oriented Dialogue Representation from Language Models

This paper investigates pre-trained language models to find out which mo...