8 papers · 1 filter
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…
Neural Induction of Finite-State Transducers
Michael Ginn, Alexis Palmer, Mans Hulden
Finite-State Transducers (FSTs) are effective models for string-to-string rewriting tasks, often providing the efficiency necessary for high-performance applications, but construct…
Speculative Decoding and the Curse of Multilinguality
Nirajan Paudel, Michael Ginn, Luc De Nardi +1
Speculative decoding is a popular technique for large language model (LLM) inference, enabling faster generation by drafting multiple tokens with a smaller draft model. However, th…
Is linguistically-motivated data augmentation worth it?
Ray Groshan, Michael Ginn, Alexis Palmer
Data augmentation, a widely-employed technique for addressing data scarcity, involves generating synthetic data examples which are then used to augment available training data. Res…
Tree Transformers are an Ineffective Model of Syntactic Constituency
Michael Ginn
Linguists have long held that a key aspect of natural language syntax is the recursive organization of language units into constituent structures, and research has suggested that c…
GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text
Michael Ginn, Lindia Tjuatja, Taiqi He +4
Language documentation projects often involve the creation of annotated text in a format such as interlinear glossed text (IGT), which captures fine-grained morphosyntactic analyse…