Papers by Kevin Yancey
Korean L2 Vocabulary Prediction: Can a Large Annotated Corpus be Used to Train Better Models for Predicting Unknown Words? (L18-1)
Copied to clipboard
| Challenge: | a recent study suggests that a classifier trained on unknown words may yield better results for L2 learners. |
| Approach: | They propose to use a supervised learning classifier to predict word complexity in Korean . they propose to train models on annotated corpus of unknown words with 71 % precision . |
| Outcome: | The proposed model recalls 80 % of unknown words with 71 % precision. |
Detecting LLM-Assisted Cheating on Open-Ended Writing Tasks on Language Proficiency Tests (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been used for open-ended writing tasks . however, there are limitations in detecting LLM-generated samples . |
| Approach: | They propose a framework for training LLM-generated text detectors that can detect LLM generated samples after being copy-typed. |
| Outcome: | The proposed model outperforms the transformer-based classifier on a high-stakes online English proficiency test. |