Papers by Alice Rozet

2 papers
Leveraging Syntactic Dependencies in Disambiguation: The Case of African American English (2024.lrec-main)

Copied to clipboard

Challenge: African American English (AAE) is a low-resource language facing the challenge of inadequate annotated data for training natural language processing models.
Approach: They propose a syntactically informed classifier for automatic disambiguation of AAE's habitual be.
Outcome: The proposed classifier improves automatic disambiguation of habitual and non-habitual meanings of "be" integrating syntactic information improves disambiguations of habituality by 65 F1 points over baseline models and as much as 74 points.
Analysis of LLM as a grammatical feature tagger for African American English (2025.findings-naacl)

Copied to clipboard

Challenge: African American English (AAE) presents unique challenges in natural language processing (NLP).
Approach: They evaluate the ability of different NLP systems to recognize distinctive AAE grammatical features by using sentence-level binary classification tasks using both zero-shot and fewshot strategies.
Outcome: The evaluation involved sentence-level binary classification tasks, using both zero-shot and few-shot strategies.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations