Papers by James Lester
Dual Process Masking for Dialogue Act Recognition (2024.findings-emnlp)
Copied to clipboard
Yeo Jin Kim, Halim Acosta, Wookhee Min, Jonathan Rowe, Bradford Mott, Snigdha Chaturvedi, James Lester
| Challenge: | Dialogue act recognition is the task of classifying conversational utterances based on their communicative intent or function. |
| Approach: | They propose a dual-processing approach that masks less important tokens in the input and enhances interpretability by using the masks applied during classification learning. |
| Outcome: | The proposed approach significantly improves performance over strong baselines for dialogue act recognition on a collaborative problem-solving dataset and three public dialogue benchmarks. |
Improving Classroom Dialogue Act Recognition from Limited Labeled Data with Self-Supervised Contrastive Learning Classifiers (2023.findings-acl)
Copied to clipboard
| Challenge: | Recognizing classroom dialogue acts has significant promise for yielding insight into teaching, student learning, and classroom dynamics. |
| Approach: | They propose to use a contrastive learning-based self-supervised approach to improve classroom dialogue act recognition from limited labeled data by increasing the accuracy of dialogue act recognization and minimizing embedding distance between the same dialogue acts. |
| Outcome: | The proposed model outperforms baseline models when trained with limited examples per dialogue act and outperformed other few-shot models that require considerably more labeled data. |