Enhancing controllability of text generation

Shcherbyna, Anton

Домівка
→
Students Research & Project Works | Роботи студентів
→
Факультет прикладних наук
→
Освітня програма наук про дані
→
2020
→
Перегляд матеріалів

dc.contributor.author	Shcherbyna, Anton
dc.date.accessioned	2020-06-17T23:16:08Z
dc.date.available	2020-06-17T23:16:08Z
dc.date.issued	2020
dc.identifier.citation	Shcherbyna, Anton. Enhancing controllability of text generation : Master Thesis : manuscript rights / Anton Shcherbyna ; Supervisor: Kostiantyn Omelianchuk ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2020. – 30 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/2240
dc.language.iso	en	uk
dc.subject	text generation	uk
dc.subject	controllability	uk
dc.subject	text modeling	uk
dc.title	Enhancing controllability of text generation	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	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.