3 papers
Smart Bilingual Focused Crawling of Parallel Documents
Cristian GarcÃa-Romero, Miquel Esplà -Gomis, Felipe Sánchez-MartÃnez
Crawling parallel texts -- texts that are mutual translations -- from the Internet is usually done following a brute-force approach: documents are massively downloaded in an unguid…
Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Model
Cristian GarcÃa-Romero, Miquel Esplà -Gomis, Felipe Sánchez-MartÃnez
Modern machine translation (MT) systems depend on large parallel corpora, often collected from the Internet. However, recent evidence indicates that (i) a substantial portion of th…
Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages
Aarón Galiano-Jiménez, Juan Antonio Pérez-Ortiz, Felipe Sánchez-MartÃnez +1
This paper explores sequence-level knowledge distillation (KD) of multilingual pre-trained encoder-decoder translation models. We argue that the teacher model's output distribution…