Apertium
Science and medicineA free/open-source machine translation platform
Get involved
Links from the organization’s published listing (2024). Older contact links may have moved.
Proposal examples
Browse the proposal library →Outcomes are reported by the linked archives.
- 2021 · acceptedApertium ↗
- 2021 · acceptedGourab Chakraborty - Developing the Hindi Bengali Language Pair ↗
- 2024 · acceptedApertium - 2024 - Chaitanya Gambali ↗
Programs & participation
14 records across 1 programIndexed project records; missing years are not zero. Coverage
2024Google Summer of CodeAnnual program · 3 projects indexed
- Capitalization Handling Module for es-pt
- Dictionary Induction from Parallel Corpora
- Spell-Checking Interface for Apertium's Web Tools
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2023Google Summer of CodeAnnual program · 5 projects indexed
- Develop a language pair for Highland Puebla Nahuatl (azz) and Western Sierra Puebla Nahuatl (nhi)
- Develop a morphological analyser
- Internationalization of Apertium Tools
- Leveraging Morphological Data from Linguistic Software Tools for Computational Resource Generation
- Tokenization for spaceless orthographies in Japanese
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2021Google Summer of CodeAnnual program · 10 projects indexed
- A morphological analyzer for Bagvalal
- Adopt an unreleased language pair, Hindi-Bhojpuri
- Adopting the Hindi-Bengali language pair (unreleased language pair).
- Apertium Browser Plugin
- Develop a prototype MT system for a strategic language pair uzb->kaa
- Finnish, Olonets-Karelian and Karelian lexicon development
- Ideas for Google Summer of Code/Morphological analyser
- Implementing new language pair: Kazakh - Uzbek
- Unipertium
- User friendly lexical training
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2020Google Summer of CodeAnnual program · 7 projects indexed
- Adopt an unreleased language pair : Hindi-Punjabi
- Adopting an unreleased language pair of Uzb-> Kaa
- Adopting the French-Arpitan language pair
- Bilingual Dictionary Discovery via Graph Exploration
- Extending Ve’rdd for Apertium Needs
- Modifying the apertium stream format and solving the markup reordering problem using wordbound blanks
- State-of-the-art Morphological Analayser for Uzbek language and improved language pairs uz-kk, uz-ky, uz-tr.
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2019Google Summer of CodeAnnual program · 10 projects indexed
- Anaphora Resolution
- Develop a releasable Uzbek-Qaraqalpaq translation pair
- English-Lingala language pair
- Improve/Extend weighted transfer rules module
- Improvement of Annotatrix project
- Improving the Catalan-Italian and Catalan-Portuguese language pairs
- Python API/library for Apertium
- Recursive Transfer
- Turkic MT improvements
- Unsupervised weighting of automata
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2018Google Summer of CodeAnnual program · 11 projects indexed
- Adopting the unreleased Romanian-Catalan pair and upgrading other pairs to the monolingual module system
- Adoption of Guarani - Spanish pair
- Apertium translation pair for Kazakh and Sakha
- Bilingual dictionary enrichment via graph completion
- Extend lttoolbox to have the power of HFST
- Fra-oci/oci-fra translator
- Improving language pairs by mining MediaWiki Content Translation postedits
- Kannada-Marathi language translation
- Tatar and Bashkir: developing a language pair
- UD-Annotatrix
- Uyghur-Turkish MT
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2017Google Summer of CodeAnnual program · 10 projects indexed
- “Proposal apertium cat-srd and ita-srd”
- Adopting English-Catalan language pair to bring it close to state-of-the-art quality
- Automatic blank handeling
- Chukchi morphological analyser using HFST
- Crimean Tatar-Turkish MT
- Development of the Czech to Russian Language Pair
- Discontiguous Multiwords
- Implementing a shallow syntactic function labeller
- Improvements to the Apertium Website Interface
- UD-annotatrix
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2016Google Summer of CodeAnnual program · 11 projects indexed
- Adopt an unreleased Kazakh-English language pair
- Apertium website improvements
- Apertium Weighted Transfer Rules
- Automatic Blank Handling
- Investigation of new ways to combining Constraint-grammar and apertium-tagger & a new averaged perception based tagger
- Kurmanji (Kurdish)-English MT
- Lint For Apertium
- Machine Translation for Sicilian-Spanish Language Pair
- New Belarusian-Russian language pair
- Project: Adopting a language pair
- Sardu, abbarra vivu!
Source checked Sep 28, 2026
Participation imported from the GSoC Organizations archive snapshot; this historical listing is not an application-status claim.
2014Google Summer of CodeAnnual program · 15 projects indexed
- Adopt the Urdu-Hindi Language Pair
- Adopting an unreleased English-Kazakh language pair
- Adopting an unreleased language pair -- Serbo-CroatianEnglish
- Adopting an unreleased language pair of Kazakh Karakalpak languages.
- Apertium on Pidgin & XChat
- Apertium-tat-rus – machine translation system from Tatar to Russian
- Assimilation evaluation toolkit for Apertium language pairs
- Bring a Hindi-English language pair up to state-of-the-art quality
- Bringing tur-kir, kaz-kir, and tur-uzb pairs out of nursery
- Complex multiwords
- Fuzzy-match repair from Translation Memory
- Improving support for non-standard text input
- Make the English-Esperanto pair state-of-the-art
- Malayalam English Language pair
- Optimise the VM for transfer
Source checked Oct 2, 2026
Community mirror of the 2009–2015 Google Melange project archive. Original Melange project links may now redirect; the participation source retains the mirrored records. Organizations without indexed projects may be absent. Imported and normalized from Vaibhav Gupta / GSoC-Data-Analyser, MIT.
2013Google Summer of CodeAnnual program · 10 projects indexed
- A Sliding-Window Drop-in Replacement for the HMM Part-of-Speech Tagger in Apertium
- Apertium Turkish-Uzbek
- Application for "Interface for creating tagged corpora" GSOC 2013
- Chinese-to-Spanish Apertium System
- Danish-Norwegian (Bokmål) language pair
- Hindi-English Language Pair
- Improvements in lexical-selection module
- Rule-based finite-state disambiguation
- Ukrainian-Russian language pair
- Visual interface for editing transfer rules
Source checked Oct 2, 2026
Community mirror of the 2009–2015 Google Melange project archive. Original Melange project links may now redirect; the participation source retains the mirrored records. Organizations without indexed projects may be absent. Imported and normalized from Vaibhav Gupta / GSoC-Data-Analyser, MIT.
2012Google Summer of CodeAnnual program · 10 projects indexed
- Apertium id-ms: Indonesian-Malaysian machine translation
- Apertium on your mobile
- Apertium-kaz-tat: machine translation between Kazakh and Tatar
- apertium-quz-spa: Machine Translation between Cuzco Quechua and Spanish
- Apertium-sl-sh: machine translation between Slovene and Serbo-Croatian
- Corpus-based lexicalised feature transfer
- Make lttoolbox-java embeddable
- New Maltese-Arabic language pair
- Rule-based finite-state disambiguation
- Turkish-Turkmen Machine Translation-Apertium
Source checked Oct 2, 2026
Community mirror of the 2009–2015 Google Melange project archive. Original Melange project links may now redirect; the participation source retains the mirrored records. Organizations without indexed projects may be absent. Imported and normalized from Vaibhav Gupta / GSoC-Data-Analyser, MIT.
2011Google Summer of CodeAnnual program · 9 projects indexed
- Adopting New Language Pair : Bengali - English
- Apertium-sl-es: machine translation between Slovene and Spanish
- Apertium-tr-az: machine translation between Turkish and Azerbaijani
- Apertium-tr-ky: New Turkish-Kyrgyz language pair.
- Implementation of a new language pair apertium-sh-mk
- Improvements to postedition interface
- New Maltese-Hebrew language pair
- Quality control framework
- VM for the transfer module
Source checked Oct 2, 2026
Community mirror of the 2009–2015 Google Melange project archive. Original Melange project links may now redirect; the participation source retains the mirrored records. Organizations without indexed projects may be absent. Imported and normalized from Vaibhav Gupta / GSoC-Data-Analyser, MIT.
2010Google Summer of CodeAnnual program · 8 projects indexed
- Apertium-fin-sme: machine translation between Finnish and Northern Sámi
- Easy dictionary maintenance
- French-Portuguese language pair for Apertium
- Improving multiword support in Apertium
- Java Runtime Port
- Morphology with HFST
- Polish-Czech language pair machine translation for Apertium
- Web-based advanced translation environment
Source checked Oct 2, 2026
Community mirror of the 2009–2015 Google Melange project archive. Original Melange project links may now redirect; the participation source retains the mirrored records. Organizations without indexed projects may be absent. Imported and normalized from Vaibhav Gupta / GSoC-Data-Analyser, MIT.
2009Google Summer of CodeAnnual program · 8 projects indexed
- Apertium going SOA
- Apertium nb2nn: machine translation between Norwegian Bokmål and Nynorsk
- Apertium-sv-da: Machine translation between Swedish and Danish
- Conversion of Anubadok: Building an English-Bengali Language Pair For Apertium
- Highly scalable web service architecture for Apertium
- Implement a Trigram Tagger for Apertium and support-tools for training it
- Java port of Apertium lttoolbox proposal
- Multi-Engine Machine Translation
Source checked Oct 2, 2026
Community mirror of the 2009–2015 Google Melange project archive. Original Melange project links may now redirect; the participation source retains the mirrored records. Organizations without indexed projects may be absent. Imported and normalized from Vaibhav Gupta / GSoC-Data-Analyser, MIT.