Papers by Junsheng Kong
Mitigating Contradictions in Dialogue Based on Contrastive Learning (2022.findings-acl)
Copied to clipboard
| Challenge: | Current chatbots generate fluent, informative responses but sometimes generate contradictory responses when interacting with human. |
| Approach: | They propose to use contrastive learning technique to mitigate contradiction issues in chatbots by minimizing the similarity between the target response and contradiction related negative example. |
| Outcome: | The proposed method outperforms existing methods on automatic and human evaluation while preserving response fluency. |
NarGINA: Towards Accurate and Interpretable Children’s Narrative Ability Assessment via Narrative Graphs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for assessing children's narrative ability are limited to evaluating completeness of narrative content and the coherence of expression, as well as interpretability of assessment results. |
| Approach: | They propose a computational framework for assessing narrative ability using a narrative graph to provide a concise and structured summary representation of narrative text. |
| Outcome: | The proposed framework achieves significant performance improvement over baselines while possessing good interpretability. |
Automated Essay Scoring via Pairwise Contrastive Regression (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to automate essay scoring use regression or ranking objectives . a novel neural pairwise ranking model is developed to optimize both objectives based on the same loss . |
| Approach: | They propose a novel Neural Pairwise Contrastive Regression model that optimizes both objectives simultaneously as a single loss. |
| Outcome: | The proposed model outperforms previous methods on the public Automated Student Assessment Prize dataset. |
TSDG: Content-aware Neural Response Generation with Two-stage Decoding Process (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Empirical results show that generative models often use a single decoder to generate a complete response at a stroke. |
| Approach: | They propose a content-aware model with two-stage decoding process to separate content words from function words. |
| Outcome: | The proposed model outperforms competing models in automatic and human evaluation on two datasets. |