5 citations · 7 across the 5 of their papers we have counts for
5 papers
Finetuning a Kalaallisut-English machine translation system using web-crawled data
Alex Jones
West Greenlandic, known by native speakers as Kalaallisut, is an extremely low-resource polysynthetic language spoken by around 56,000 people in Greenland. Here, we attempt to fine…
A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space
Alex Jones, William Yang Wang, Kyle Mahowald
In cross-lingual language models, representations for many different languages live in the same space. Here, we investigate the linguistic and non-linguistic factors affecting sent…
Sentiment-based Candidate Selection for NMT
Alex Jones, Derry Tanti Wijaya
The explosion of user-generated content (UGC)--e.g. social media posts, comments, and reviews--has motivated the development of NLP applications tailored to these types of informal…
Majority Voting with Bidirectional Pre-translation For Bitext Retrieval
Alex Jones, Derry Tanti Wijaya
Obtaining high-quality parallel corpora is of paramount importance for training NMT systems. However, as many language pairs lack adequate gold-standard training data, a popular ap…
Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages
Garry Kuwanto, Afra Feyza Akyürek, Isidora Chara Tourni +3
We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data…