Emerging TechnologiesTranslation

How Does Machine Translation Work? | Rosalia Ignatova

Next Page Foundation
document

Presented under the opening title “Attention Is All You Need,” Rosalia Ignatova’s “How Does Machine Translation Work?” formed part of Thinking Literature in Translation in November 2025. The presentation introduces the Transformer architecture and explains why attention mechanisms became foundational to contemporary machine translation and generative language models.

Ignatova describes how self-attention allows a model to evaluate relationships among all the words in a sequence. Token embeddings and query, key and value vectors enable the system to interpret context and long-range dependencies, while decoder-only models use large-scale multilingual training to generate coherent text without a separate encoder.

English-to-Bulgarian literary examples produced by systems including Claude and ChatGPT demonstrate both the fluency and the limitations of machine-generated translations. The presentation considers terminology, pronoun reference, rhythm, register and stylistic consistency, comparing direct or zero-shot translation with approaches that first provide the model with explanations and contextual guidance.

Poetry and culturally specific writing receive particular attention because technically correct output may still lose ambiguity, sound, humour or imaginative force. Ignatova ultimately distinguishes computational capacity from human creativity: AI can support analysis and produce useful drafts, but literary translation continues to depend on interpretation, aesthetic judgement and purposeful human decisions.

 

Download this presentation here.

From the same theme

How Is AI Navigated by Literary Translators? | Ela Varošanec Krsnik

How Is AI Navigated by Literary Translators? | Ela Varošanec Krsnik

Sep 2026 ENG
Translation TechnologyArtificial intelligence

How Can Publishing Embrace AI? | Michalis Kalamaras

How Can Publishing Embrace AI? | Michalis Kalamaras

ENG
Tech TrendsArtificial intelligence

Literature from Bosnia and Herzegovina in Translation into European Languages: Study (2015–2020) | Alma Mešić and Muamera Smajić

Literature from Bosnia and Herzegovina in Translation into European Languages: Study (2015–2020) | Alma Mešić and Muamera Smajić

Sep 2026 BOS
Translation MarketsTranslation Publishing

Report on Translation (2015–2020): Data, Analysis and Recommendations for Montenegro | Vladimir Vojinović, Dragana Marković, Sanja Vojinović, Barbara Simović and Miloš Milačić

Report on Translation (2015–2020): Data, Analysis and Recommendations for Montenegro | Vladimir Vojinović, Dragana Marković, Sanja Vojinović, Barbara Simović and Miloš Milačić

CNR
Translation MarketsTranslation Publishing

Albanian Literature from Kosovo in Translation (2015–2020) | Ardian Kyçyku

Albanian Literature from Kosovo in Translation (2015–2020) | Ardian Kyçyku

SQI
Translation PublishingTranslation Markets

Voice, Echo: Serbian Literature in Translation (2015–2020) | Dejan Aleksić

Voice, Echo: Serbian Literature in Translation (2015–2020) | Dejan Aleksić

SRP
Translation Markets

All Drivers Included! Macedonian Literature in Translation (2015–2020) | Robert Alagjozovski

All Drivers Included! Macedonian Literature in Translation (2015–2020) | Robert Alagjozovski

MKD
Translation MarketsTranslation Publishing

Mapping Translated Literatures from the Western Balkans (2015–2020) | Aida Čengić and Next Page Foundation

Mapping Translated Literatures from the Western Balkans (2015–2020) | Aida Čengić and Next Page Foundation

ENG
Translation Markets