6 citations · 8 across the 7 of their papers we have counts for
7 papers
Linguistically Informed Evaluation of Multilingual ASR for African Languages
Fei-Yueh Chen, Lateef Adeleke, C. M. Downey
Word Error Rate (WER) mischaracterizes ASR models' performance for African languages by combining phonological, tone, and other linguistic errors into a single lexical error. By co…
Targeted Multilingual Adaptation for Low-resource Language Families
C. M. Downey, Terra Blevins, Dhwani Serai +2
The "massively-multilingual" training of multilingual models is known to limit their utility in any one language, and they perform particularly poorly on low-resource languages. Ho…
Embedding structure matters: Comparing methods to adapt multilingual vocabularies to new languages
C. M. Downey, Terra Blevins, Nora Goldfine +1
Pre-trained multilingual language models underpin a large portion of modern NLP tools outside of English. A strong baseline for specializing these models for specific languages is…
Planting and Mitigating Memorized Content in Predictive-Text Language Models
C. M. Downey, Wei Dai, Huseyin A. Inan +3
Language models are widely deployed to provide automatic text completion services in user products. However, recent research has revealed that language models (especially large one…
Learning to translate by learning to communicate
C. M. Downey, Xuhui Zhou, Leo Z. Liu +1
We formulate and test a technique to use Emergent Communication (EC) with a pre-trained multilingual model to improve on modern Unsupervised NMT systems, especially for low-resourc…
Multilingual unsupervised sequence segmentation transfers to extremely low-resource languages
C. M. Downey, Shannon Drizin, Levon Haroutunian +1
We show that unsupervised sequence-segmentation performance can be transferred to extremely low-resource languages by pre-training a Masked Segmental Language Model (Downey et al.,…
A Masked Segmental Language Model for Unsupervised Natural Language Segmentation
C. M. Downey, Fei Xia, Gina-Anne Levow +1
Segmentation remains an important preprocessing step both in languages where "words" or other important syntactic/semantic units (like morphemes) are not clearly delineated by whit…