6 papers
Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation
Ali Marashian, Alexis Palmer, Katharina von der Wense
The rapid rise in popularity of large language models (LLMs) for translation calls for a thorough study of the reliability of their confidence in their own outputs. Unlike many gen…
Massively Multilingual Joint Segmentation and Glossing
Michael Ginn, Lindia Tjuatja, Enora Rice +5
Automated interlinear gloss prediction with neural networks is a promising approach to accelerate language documentation efforts. However, while state-of-the-art models like GlossL…
Untangling the Influence of Typology, Data and Model Architecture on Ranking Transfer Languages for Cross-Lingual POS Tagging
Enora Rice, Ali Marashian, Hannah Haynie +2
Cross-lingual transfer learning is an invaluable tool for overcoming data scarcity, yet selecting a suitable transfer language remains a challenge. The precise roles of linguistic…
From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation
Ali Marashian, Enora Rice, Luke Gessler +2
Many of the world's languages have insufficient data to train high-performing general neural machine translation (NMT) models, let alone domain-specific models, and often the only…
Measuring Contextual Informativeness in Child-Directed Text
Maria Valentini, Téa Wright, Ali Marashian +3
To address an important gap in creating children's stories for vocabulary enrichment, we investigate the automatic evaluation of how well stories convey the semantics of target voc…
TAMS: Translation-Assisted Morphological Segmentation
Enora Rice, Ali Marashian, Luke Gessler +2
Canonical morphological segmentation is the process of analyzing words into the standard (aka underlying) forms of their constituent morphemes. This is a core task in language docu…