Sarah Moeller
Assistant Professor
- Gainesville FL UNITED STATES
- College of Liberal Arts and Sciences
Sarah Moeller's research focuses on applying computational methods to documentary and descriptive linguistics.
Contact More Open optionsBiography
Sarah Moeller is a professor in the Department of Linguistics in the College of Liberal Arts and Sciences. Her research is focused on applying computational methods to documentary and descriptive linguistics. She also is working to improve natural language processing systems using insights from linguistic analysis. Sarah also has an interest in minority languages of the former Soviet Union, where she first encountered language endangerment and did fieldwork on the Nakh-Daghestanian languages.
Areas of Expertise
Social
Articles
Computational Morphology for Language Documentation and Description
Colorado Research in LinguisticsSarah Moeller
2021-08-22
During this time of heightened interest in computational methods for low-resource languages an important question needs to explored: What [computational] methods...can detect [morphological] structure in small, noisy data sets, while being directly applicable to a wide variety of languages?” (Bird, 2009). This paper provides an overview of common natural language processing (NLP) methods and how those methods have been applied to the study of morphology, particularly in low-resource languages (LRL).
Designing a Uniform Meaning Representation for Natural Language Processing
Technical ContributionSarah Moeller, et al.
2021-04-30
Researchers present Uniform Meaning Representation (UMR), a meaning representation designed to annotate the semantic content of a text. UMR is primarily based on Abstract Meaning Representation (AMR), an annotation framework initially designed for English, but also draws from other meaning representations.
To POS Tag or Not to POS Tag: The Impact of POS Tags on Morphological Learning in Low-Resource Settings
Association for Computational LinguisticsSarah Moeller, et al.
2021-08-01
Part-of-Speech (POS) tags are routinely included as features in many NLP tasks. However, the importance and usefulness of POS tags needs to be examined as NLP expands to low-resource languages because linguists who provide many annotated resources do not place priority on early identification and tagging of POS. This paper describes an empirical study about the effect that POS tags have on two computational morphological tasks with the Transformer architecture.
