Papers by Jiamin Luo
How to Understand “Support”? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on Weakly-supervised Phrase Grounding (WPG) largely ignore the implicit phrase-region matching relations, rendering it arduous to explore the semantic nature of phrases. |
| Approach: | They propose an Implicit-Enhanced Causal Inference approach to address the challenges of modeling the implicit relations and highlighting them beyond the explicit. |
| Outcome: | The proposed approach outperforms the state-of-the-art baselines on an implicit-enhanced dataset. |
ChatASU: Evoking LLM’s Reflexion to Truly Understand Aspect Sentiment in Dialogues (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on interactive ASU ignore the coreference issue for opinion targets while this phenomenon is ubiquitous in interactive scenarios especially dialogues, limiting the ASU performance. |
| Approach: | They propose a Chat-based Aspect Sentiment Understanding task that integrates various NLP tasks with the chat paradigm and propose 'trusted self-reflexion' approach with ChatGLM as backbone to address aspect coreference issue. |
| Outcome: | The proposed task outperforms state-of-the-art baselines and shows that it is highly effective. |
TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies focus on learning contextual information in conversations, neglecting acoustic and vision topic information. |
| Approach: | They propose a model-agnostic Topic-enriched Diffusion approach for capturing multimodal topic information in MCE tasks. |
| Outcome: | The proposed approach improves over the state-of-the-art MCE models and the existing models. |