Yang, Zijian Győző, Laki, László János (2023) Solving Hungarian natural language processing tasks with multilingual generative models Annales Mathematicae et Informaticae. 57. pp. 92-106. ISSN 1787-6117 (Online)
pdf
92_106.pdf Download (597kB) [error in script] |
Absztrakt (kivonat)
Generative ability is a crucial need for artificial intelligence applications, such as chatbots, virtual assistants, machine translation systems etc. In recent years, the transformer-based neural architectures gave a huge boost to generate human-like English texts. In our research we did experiments to create pre-trained generative transformer models for Hungarian language and fine-tune them for multiple types of natural language processing tasks. In our focus, multilingual models were trained. We have pre-trained a multilingual BART, then fine-tuned it to various NLP tasks, such as text classification, abstractive summarization. In our experiments, we focused on transfer learning techniques to increase the performance. Furthermore, a M2M100 multilingual model was fine-tuned for a 12-lingual HungarianCentric machine translation. Last but not least, a Marian NMT based machine translation system was also built from scratch for the 12-lingual Hungarian-Centric machine translation task. In our results, using the cross-lingual transfer method we could achieve higher performance in all of our tasks. In our machine translation experiment, using our fine-tuned M2M100 model we could outperform the Google Translate, Microsoft Translator and eTranslation.
Mű típusa: | Folyóiratcikk - Journal article |
---|---|
Szerző: | Szerző neve Email MTMT azonosító ORCID azonosító Közreműködés Yang, Zijian Győző NEM RÉSZLETEZETT NEM RÉSZLETEZETT NEM RÉSZLETEZETT Szerző Laki, László János NEM RÉSZLETEZETT NEM RÉSZLETEZETT NEM RÉSZLETEZETT Szerző |
Kapcsolódó URL-ek: | |
Kulcsszavak: | natural language processing, multilingual model, sentiment analysis, abstractive summarization, machine translation, Marian NMT, M2M100 |
Nyelv: | angol |
Kötetszám: | 57. |
DOI azonosító: | 10.33039/ami.2022.11.001 |
ISSN: | 1787-6117 (Online) |
Felhasználó: | Tibor Gál |
Dátum: | 08 Jan 2023 10:43 |
Utolsó módosítás: | 11 Aug 2023 06:59 |
URI: | http://publikacio.uni-eszterhazy.hu/id/eprint/7594 |
Tétel nézet |