Welcome to the LCR-ADS Lab
The LCR-ADS (Learner Corpus Research and Applied Data Science) lab at the University of Oregon conducts linguistic research related to language development and assessment (primarily with second language users). We develop, test, and implement linguistic analysis methods, collect and annotate corpora, and develop and evaluate language assessment tools (primarily related to language production tasks).
Recently Published
-
Building custom NLP tools to annotate discourse-functional features for second language writing research (A tutorial) (2024)
In Research Methods in Applied Linguistics
-
Evaluating NLP models with written and spoken L2 samples (2024)
In Research Methods in Applied Linguistics
-
The relationship between L2 spanish proficiency and features of written lexical and lexicogrammatical use (2024)
In Applied Linguistics
-
Annotation Scheme for English Argument Structure Constructions Treebank (2024)
In Proceedings of The 18th Linguistic Annotation Workshop (LAW-XVIII)
-
Assessing spoken lexical and lexicogrammatical proficiency using features of word, bigram, and dependency bigram use (2023)
In The Modern Language Journal
-
Span identification of epistemic stance-taking in academic written english (2023)
In Proceedings the 18th Workshop on Innovative Use of NLP for Building Educational Applications
Project Repositories
-
LxGrTagger-Doc (2024-)
This documentation page provides detailed descriptions of the ongoing project aimed at refining the Lexicogrammatical Tagger (LxGrTgr).
-
TAALES_ES (2023)
This repository includes the code for the Spanish Version of TAALES.
-
ASC-Treebank (2023)
This repository includes the argument structure construction (ASC) Treebank.
-
SL2E-Dependency-Treebank (2022)
This repository includes the dependency treebank of spoken L2 English (SL2E).
-
TAALED (2022)
This repository includes the tool for automatic assessment of lexical diversity.
Ongoing Projects
- We are using our argument structure construction (ASC) annotation tool to explore how the use of ASC characteristics (e.g., the strength of association between a verb and the ASC it employs) correlates with proficiency in second language writing and speaking.
- We are currently refining the Lexicogrammatical Tagger (LxGrTgr) and assessing its accuracy across various registers.