| The evolution of Natural Language Processing: from rules through neural networks to generative AI. What does the future hold? | Evolucija obrade prirodnog jezika: od pravila preko neuronskih mreža do generativne AI. Šta donosi budućnost? |
| JUDIG_en_sr, [pdf] | JUDIG_en_sr, [pdf] |
| ID: 18.1.1.03 Number: 1 Volume: 1 Month: 11 Year: 2024 UDC: [tmx] [bow] |
| Ruslan Mitkov | Ruslan Mitkov |
Abstract
Natural Language Processing (NLP) is undergoing dynamic and unprecedented changes as never before. While we have always known that NLP is not a magic technology which always has been far from 100% accurate, the landscape of Language and Translation Technology is changing. First Deep Learning methods and now Large Language Models, have taken the world by storm. This easy-to-follow and entertaining talk will seek to shed light on the future of Natural Language Processing in the Artificial Intelligence (AI) era.
The keynote will sketch the history of Natural Language Processing and Machine Translation and will review the latest advances powered by Deep Learning and Large Language Models (LLMs). It will then critically look at the employment of LLMs in Natural Language Processing and Machine Translation (and the evolution of NLP methods will be exemplified by) reporting on recent original research of the speaker which compares LLMs, Deep Learning, and rule-based approaches for selected NLP tasks and applications. | Apstrakt
Obrada prirodnog jezika (OPJ) prolazi kroz dinamične i neslućene promene. Oduvek smo znali da obrada prirodnih jezika nije magična tehnologija jer su njeni rezultati nisu bili ni blizu 100% tačni, oblast tehnologije jezika i prevođenja se menja. Metode dubokog učenja, a zatim i veliki jezički modeli, munjevito su osvojili svet. Ovo zabavno predavanje koje se lako prati nastojaće da osvetli budućnost obrade prirodnih jezika u eri veštačke inteligencije (VI).
Predavanje će skicirati istoriju obrade prirodnih jezika i mašinskog prevođenja i dati pregled najnovijih dostignuća zasnovanih na dubokom učenju i velikim jezičkim modelima (LLM). Zatim će biti dat kritički osvrt na primenu velikih jezičkih modela u obradi prirodnog jezika i mašinskom prevođenju, kroz prikaz nedavnih istraživanja predavača u kojima upoređuje velike jezičke modele, duboko učenje i pristupe zasnovane na pravilima za odabrane zadatke obrade prirodnog jezika i konkretne primene.
Prikazane studije slučaja će poslužiti kao osnova za nastavak |