Add to ORKGThis study discusses the effect of semi-supervised learning in combination with pretrained language models for data-to-text generation. It is not known whether semi-supervised learning is still helpful when a large-scale language model is also supplemented. This study aims to answer this question by comparing a data-to-text system only supplemented with a language model, to two data-to-text systems that are additionally enriched by a data augmentation or a pseudo-labeling semi-supervised learning approach. Results show that semi-supervised learning results in higher scores on diversity metrics. In terms of output quality, extending the training set of a data-to-text system with a language model using the pseudo-labeling approach did incre...
Recent advances in deep neural language models combined with the capacity of large scale datasets ha...
Data annotation is the process of labeling text, images, or other types of content for machine learn...
At the computational level, language is often assumed to require both supervised and unsupervised le...
This study discusses the effect of semi-supervised learning in combination with pretrained language ...
Within a situation where Semi-Supervised Learning (SSL) is available to exploit unlabeled data, this...
Author's accepted manuscriptGood performance in supervised text classification is usually obtained w...
This paper studies the use of language models as a source of synthetic unlabeled text for NLP. We fo...
In recent years, language models (LMs) have made remarkable progress in advancing the field of natu...
International audienceIn Natural Language Generation (NLG), End-to-End (E2E) systems trained through...
In text classification tasks, fine tuning pretrained language models like BERT and GPT-3 yields comp...
The collection and curation of high-quality training data is crucial for developing text classificat...
In Natural Language Processing (NLP), applications trained on downstream tasks for text classificati...
Language model fine-tuning is essential for modern natural language processing, but is computational...
In many cases of machine learning, research suggests that the development of training data might hav...
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on...
Recent advances in deep neural language models combined with the capacity of large scale datasets ha...
Data annotation is the process of labeling text, images, or other types of content for machine learn...
At the computational level, language is often assumed to require both supervised and unsupervised le...
This study discusses the effect of semi-supervised learning in combination with pretrained language ...
Within a situation where Semi-Supervised Learning (SSL) is available to exploit unlabeled data, this...
Author's accepted manuscriptGood performance in supervised text classification is usually obtained w...
This paper studies the use of language models as a source of synthetic unlabeled text for NLP. We fo...
In recent years, language models (LMs) have made remarkable progress in advancing the field of natu...
International audienceIn Natural Language Generation (NLG), End-to-End (E2E) systems trained through...
In text classification tasks, fine tuning pretrained language models like BERT and GPT-3 yields comp...
The collection and curation of high-quality training data is crucial for developing text classificat...
In Natural Language Processing (NLP), applications trained on downstream tasks for text classificati...
Language model fine-tuning is essential for modern natural language processing, but is computational...
In many cases of machine learning, research suggests that the development of training data might hav...
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on...
Recent advances in deep neural language models combined with the capacity of large scale datasets ha...
Data annotation is the process of labeling text, images, or other types of content for machine learn...
At the computational level, language is often assumed to require both supervised and unsupervised le...