Sentence Detailing and Its Applications


ŞAHİN F., AMASYALI M. F.

2023 Innovations in Intelligent Systems and Applications Conference, ASYU 2023, Sivas, Turkey, 11 - 13 October 2023 identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/asyu58738.2023.10296831
  • City: Sivas
  • Country: Turkey
  • Keywords: commonsense knowledge, data augmentation, deep learning, natural language generation, natural language processing, text-to-text transformer
  • Yıldız Technical University Affiliated: Yes

Abstract

The purpose of this study is to observe whether there is a performance improvement when we train the multilingual Text-to-Text Transfer Transformer (mT5), which is a transformer model in Natural Language Processing (NLP), with a dataset having sentences constructed using a set of given words as a pre-process before we train the model with a text-from-title dataset directly. Given words were considered as concept-set and the model was expected to learn the concept like commonsense knowledge from news to generate appropriate sentences after being trained with title-to-text dataset as well. We named this method 'Sentence Detailing' due to its feature of generating sentences by adding details to a set of words. In addition to the text generation from title, we also examined this method under the topic of data augmentation.