Usage of lstm models for natural language understanding

Daniiel, Y.; Onyshchenko, K.; Kameniuk, N.

Публікація:
Usage of lstm models for natural language understanding

dc.contributor.author	Daniiel, Y.
dc.contributor.author	Onyshchenko, K.
dc.contributor.author	Kameniuk, N.
dc.date.accessioned	2024-05-23T13:10:38Z
dc.date.available	2024-05-23T13:10:38Z
dc.date.issued	2021
dc.description.abstract	The problem of emotion classification is a complex task of language interpretation. In this work, a number of existing solutions for emotional classification problem were considered. The evaluation of performance of the considered models was conducted. The model for emotion classification in three-sentence conversations is proposed in this work. The model is based on smileys and word embeddings with domain specificity in state of art conversations on the Internet. The model performance is evaluated and compared with language processing model BERT. The proposed model is better at classifying emotions than BERT (F1 78 versus 75). However, modern performance of models for language representation did not achieve the human performance due to the complexity of natural language. There is a variety of factors to consider when choosing the word embeddings and training methods to design the model architecture.
dc.identifier.citation	Daniiel Y. Usage of lstm models for natural language understanding / Y. Daniiel, K. Onyshchenko, N. Kameniuk // Бионика интеллекта. – 2021. – № 2 (97). – С. 20–26. – DOi: https://doi.org/10.30837/ bi.
dc.identifier.doi	https://doi.org/10.30837/ bi
dc.identifier.uri	https://openarchive.nure.ua/handle/document/26573
dc.language.iso	uk
dc.publisher	ХНУРЕ
dc.subject	natural language processing
dc.subject	neural network
dc.subject	natural language
dc.title	Usage of lstm models for natural language understanding
dc.type	Article
dspace.entity.type	Publication