SeamlessM4T-Massively Multilingual & Multimodal Machine Translation.
Seamless CommunicationLoïc BarraultYu-An ChungMariano Cora MeglioliDavid DaleNing DongPaul-Ambroise DuquenneHady ElsaharHongyu GongKevin HeffernanJohn HoffmanChristopher KlaiberPengwei LiDaniel LichtJean MaillardAlice RakotoarisonKaushik Ram SadagopanGuillaume WenzekEthan YeBapi AkulaPeng-Jen ChenNaji El HachemBrian EllisGabriel Mejia GonzalezJustin HaaheimPrangthip HansantiRuss HowesBernie HuangMin-Jae HwangHirofumi InagumaSomya JainElahe KalbassiAmanda KalletIlia KulikovJanice LamDaniel LiXutai MaRuslan MavlyutovBenjamin PeloquinMohamed RamadanAbinesh RamakrishnanAnna Y. SunKevin TranTuan TranIgor TufanovVish VogetiCarleigh WoodYilin YangBokai YuPierre AndrewsCan BaliogluMarta R. Costa-jussàOnur CelebiMaha ElbayadCynthia GaoFrancisco GuzmánJustine KaoAnn LeeAlexandre MourachkoJuan PinoSravya PopuriChristophe RopersSafiyyah SaleemHolger SchwenkPaden TomaselloChanghan WangJeff WangSkyler WangPublished in: CoRR (2023)
Keyphrases
- machine translation
- cross lingual
- language resources
- language independent
- cross language information retrieval
- language specific
- multilingual documents
- chinese english
- machine translation system
- natural language processing
- cross lingual information retrieval
- information extraction
- comparable corpora
- parallel corpus
- language processing
- word sense disambiguation
- parallel corpora
- cross language
- statistical machine translation
- natural language
- natural language generation
- target language
- translation model
- query translation
- bilingual dictionaries
- word alignment
- word segmentation
- linguistic resources
- digital libraries
- finite state transducers
- brazilian portuguese
- source language
- word level
- expert systems
- artificial intelligence
- bilingual lexicon