Пошук академічних текстів

Інформація × Реєстраційний номер 2120U007892, Матеріали видань та локальних репозитаріїв Категорія Препринт Назва роботи Enhancing controllability of text generation Автор Shcherbyna AntonShcherbyna Anton Дата публікації 01-01-2020 Постачальник інформації Український католицький університет Першоджерело https://hdl.handle.net/20.500.14570/2240 Видання Опис Many models could generate text conditioned on some context, but those approaches don’t provide us with the ability to control various aspects of the generated text (e.g., sentiment). To address this problem, Variational Autoencoder is typically used because they give the ability to manipulate in latent space and, in this way,control text generation. However, it has been shown that VAE with strong autoregressive decoders,which are used for text modeling, faces posterior collapse problem. We think that one of the reasons why this problem occurs is a restrictive gaussian assumption we made about approximate posterior. In this work, we want to apply well-known approaches based on Normalizing Flows to improve approximate posterior for text modeling and check if it can help avoid posterior collapse. Додано в НРАТ 2025-11-05 Закрити