Papers by Varun Nathan
Investigating the Role and Impact of Disfluency on Summarization (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Existing studies have focused on disfluency detection and removal, with limited studies into its impact on downstream tasks. |
| Approach: | They propose to incorporate disfluency in summarization models to reduce the impact of replacement disfluencies on natural language processing tasks. |
| Outcome: | The proposed model improves on both public and real-life datasets and shows that it can handle disfluent data with up to 6.99-point degradation in Rouge-L score and replacement disfluencies have the highest negative impact. |
Mirage: A Diagnostic Framework for Evaluating the Realism of Synthetic Contact Center Dialogue Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | capturing the full realism of real agent–customer interactions remains a challenge . privacy constraints and data scarcity limit the availability of real conversations . |
| Approach: | They propose a diagnostic evaluation framework for synthetic dialogue generation . they benchmarked strategies guided by structured supervision on call attributes . |
| Outcome: | The proposed framework outperforms synthetic transcripts on quality assurance tasks . it shows that current generation strategies lack sentiment fidelity, disfluency modeling, behavioral variation and conversational realism . |