Machine Translation in the Era of Large Language Models:A Survey of Historical and Emerging Problems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AYAI4QMWL" target="_blank" >RIV/00216208:11320/26:YAI4QMWL - isvavai.cz</a>

Výsledek na webu

<a href="https://www.mdpi.com/2078-2489/16/9/723" target="_blank" >https://www.mdpi.com/2078-2489/16/9/723</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/info16090723" target="_blank" >10.3390/info16090723</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Machine Translation in the Era of Large Language Models:A Survey of Historical and Emerging Problems

Popis výsledku v původním jazyce

Historically regarded as one of the most challenging tasks presented to achieve complete artificial intelligence (AI), machine translation (MT) research has seen continuous devotion over the past decade, resulting in cutting-edge architectures for the modeling of sequential information. While the majority of statistical models traditionally relied on the idea of learning from parallel translation examples, recent research exploring self-supervised and multi-task learning methods extended the capabilities of MT models, eventually allowing the creation of general-purpose large language models (LLMs). In addition to versatility in providing translations useful across languages and domains, LLMs can in principle perform any natural language processing (NLP) task given sufficient amount of task-specific examples. While LLMs now reach a point where they can both replace and augment traditional MT models, the extent of their advantages and the ways in which they leverage translation capabilities across multilingual NLP tasks remains a wide area for exploration. In this literature survey, we present an introduction to the current position of MT research with a historical look at different modeling approaches to MT, how these might be advantageous for the solution of particular problems, and which problems are solved or remain open in regard to recent developments. We also discuss the connection of MT models leading to the development of prominent LLM architectures, how they continue to support LLM performance across different tasks by providing a means for cross-lingual knowledge transfer, and the redefinition of the task with the possibilities that LLM technology brings. © 2025 by the authors.

Název v anglickém jazyce

Machine Translation in the Era of Large Language Models:A Survey of Historical and Emerging Problems

Popis výsledku anglicky

Historically regarded as one of the most challenging tasks presented to achieve complete artificial intelligence (AI), machine translation (MT) research has seen continuous devotion over the past decade, resulting in cutting-edge architectures for the modeling of sequential information. While the majority of statistical models traditionally relied on the idea of learning from parallel translation examples, recent research exploring self-supervised and multi-task learning methods extended the capabilities of MT models, eventually allowing the creation of general-purpose large language models (LLMs). In addition to versatility in providing translations useful across languages and domains, LLMs can in principle perform any natural language processing (NLP) task given sufficient amount of task-specific examples. While LLMs now reach a point where they can both replace and augment traditional MT models, the extent of their advantages and the ways in which they leverage translation capabilities across multilingual NLP tasks remains a wide area for exploration. In this literature survey, we present an introduction to the current position of MT research with a historical look at different modeling approaches to MT, how these might be advantageous for the solution of particular problems, and which problems are solved or remain open in regard to recent developments. We also discuss the connection of MT models leading to the development of prominent LLM architectures, how they continue to support LLM performance across different tasks by providing a means for cross-lingual knowledge transfer, and the redefinition of the task with the possibilities that LLM technology brings. © 2025 by the authors.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Information (Switzerland)

ISSN

2078-2489

e-ISSN

—

Svazek periodika

16

Číslo periodika v rámci svazku

9

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

28

Strana od-do

723

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-105017509121