Generation of sport news articles from match text commentary

Porplenko, Denys

Home
→
Students Research & Project Works | Роботи студентів
→
Факультет прикладних наук
→
Освітня програма наук про дані
→
2020
→
View Item

dc.contributor.author	Porplenko, Denys
dc.date.accessioned	2020-01-28T13:50:28Z
dc.date.available	2020-01-28T13:50:28Z
dc.date.issued	2020
dc.identifier.citation	Porplenko, Denys. Generation of sport news articles from match text commentary : Master Thesis : manuscript rights / Denys Porplenko ; Supervisor PhD. Valentin Malykh ; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2020. – 72 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/1905
dc.language.iso	en	uk
dc.subject	Cross-entropy	uk
dc.subject	recurrent neural network	uk
dc.subject	Long short-term memory	uk
dc.title	Generation of sport news articles from match text commentary	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	Nowadays, thousands of sporting events take place every day. Most of the sports news (results of sports competitions) is written by hand, despite their pattern structure. In this work, we want to check possible or not to generate news based on the broadcast - a set of comments that describe the game in real-time. This problem solves for the Russian language and considered as a summarization problem, using extractive and abstract approaches. Among extractive models, we do not get signiﬁcant results. However, we build an Oracle model that showed the best possible result equal to 0.21 F1 for ROUGE-1. For the abstraction approach, we get 0.26 F1 for the ROUGE-1 score using the NMT framework, the Bidirectional Encoder Representations from Transformers (BERT), as an encoder and text augmentation based on a thesaurus. Other types of encoders do not show signiﬁcant improvements.	uk