In this work, we propose ProtAugment, a meta-learning algorithm for short texts classification (the intent detection task). ProtAugment is a novel extension of ...
May 27, 2021 · ProtAugment is the state-of-the-art method for intent detection meta-learning, at no extra labeling efforts and without the need to fine-tune a conditional ...
Aug 1, 2021 · PROTAUGMENT is the state- of-the-art method for intent detection meta- learning, at no extra labeling efforts and with- out the need to fine- ...
This repository contains the official code for the paper PROTAUGMENT: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning.
This work proposes PROTAUGMENT, a meta-learning algorithm for short texts classification applied to the intent detection task, a novel extension of ...
PROTAUGMENT (Dopierre, Gravier, and Logerais 2021) introduces a short-text paraphrasing model that produces diverse paraphrases of the original text as data ...
Jun 1, 2021 · Bibliographic details on ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning.
This model is used to generate paraphrases. It has been trained on a mix of 3 different paraphrase detection datasets: MSR, Quora, Google-PAWS.
People also ask
Is Meta Learning supervised or Unsupervised?
What is meta learning in deep learning?
May 27, 2021 · PROTAUGMENT: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning. Thomas Dopierre12 and Christophe Gravier1 and.
ProtAugment: Intent Detection Meta-Learning through Unsupervised Diverse Paraphrasing ... It relies on diverse paraphrasing: a conditional language model is first ...