Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Text mining›Machine Translation
Process / pipeline

Machine Translation

Also known as: MT, neural machine translation, automatic translation, Makine Çevirisi (Machine Translation)

Machine translation (MT) is a natural-language-processing task that automatically converts text in one language into another. Modern MT is built on neural sequence-to-sequence models — the attention mechanism introduced by Bahdanau et al. (2015) and the transformer architecture of Vaswani et al. (2017) — and it widens access to sources for multilingual data analysis and research.

ScholarGate
  1. Process / pipeline
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Machine Translation
Cross-lingual Text Analy…POS TaggingSentiment AnalysisNatural Language Generat…Question Answering

When to use it

Use machine translation when you have source-language text and need it in another language, and a trained model for that language pair is available. It suits widening source access in multilingual data analysis and research. For specialised-domain text, expect to fine-tune the model. At least a small amount of text is needed to translate.

Strengths & limitations

Strengths
  • Widens access to sources by making text in other languages usable for analysis and research.
  • Neural attention and transformer models translate whole sentences in context rather than word by word.
  • Scales from short passages to large multilingual corpora through the same model.
Limitations
  • Requires an available trained model for the specific source and target language pair.
  • Specialised-domain translation may need fine-tuning before it is accurate enough.
  • Output must still be checked for fidelity and fluency; errors can be subtle.

Frequently asked

What kind of model does machine translation use?

Modern MT uses neural sequence-to-sequence models. The attention mechanism (Bahdanau et al., 2015) lets the model align source and target as it translates, and the transformer architecture (Vaswani et al., 2017), built entirely on attention, underpins current systems.

Do I need a model for my specific language pair?

Yes. A trained model for the source and target language pair must be available. Without coverage for that pair, the system cannot produce usable translations.

Why might translation quality be poor on my texts?

Specialised-domain material often needs fine-tuning. A general model may translate everyday language well but struggle with domain-specific terminology until it is adapted on in-domain text.

Should I trust the output directly?

Check it. Translated output should be evaluated for fidelity to the source and fluency in the target language before it feeds into further analysis, since errors can be subtle.

Sources

  1. Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. International Conference on Learning Representations (ICLR). link ↗
  2. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. & Polosukhin, I. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems (NeurIPS). link ↗

How to cite this page

ScholarGate. (2026, June 1). Machine Translation. ScholarGate. https://scholargate.app/en/text-mining/machine-translation

Related methods

Cross-lingual Text AnalysisPOS TaggingSentiment Analysis

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Cross-lingual Text AnalysisText mining↔ compare
  • POS TaggingText mining↔ compare
  • Sentiment AnalysisText mining↔ compare
Compare side by side →

Referenced by

Natural Language GenerationQuestion Answering

Similar methods

Multilingual TransformerSequence-to-Sequence ModelTransformerText SummarizationAttention MechanismMultilingual text summarizationMultilingual question answeringLanguage Identification

Related reference concepts

Machine TranslationMachine TranslationNatural Language ProcessingSequence-to-Sequence Models and TransformersComputational LinguisticsMachine Translation and the Translation Profession

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Machine Translation (Machine Translation). Retrieved 2026-07-21 from https://scholargate.app/en/text-mining/machine-translation · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Type
NLP text-to-text generation task
Approaches
Neural sequence-to-sequence (attention / transformer)
Input
Source-language text
Output
Target-language text
KeyIdeas
Attention (Bahdanau et al., 2015); Transformer self-attention (Vaswani et al., 2017)
Related methods
Cross-lingual Text AnalysisPOS TaggingSentiment Analysis
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account