Papers with visual dialogue game
LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue (2022.findings-aacl)
Copied to clipboard
| Challenge: | Generating coherent, human-like text for dialogue remains a challenge . lack of careful design of rewards can lead to mode-collapse in dialogue . |
| Approach: | They propose a theoretical framework for learning to generate text in dialogue . they propose to use data-shift to develop theoretical guarantees for learners . |
| Outcome: | The proposed framework improves both task-success and human-likeness of the generated text. |
Learning to Generate Equitable Text in Dialogue from Biased Training Data (2023.acl-long)
Copied to clipboard
| Challenge: | Absence of equitable and inclusive principles can hinder the formation of common ground, which in turn negatively impacts the overall performance of the system. |
| Approach: | They propose to use theories of computational learning to study equitable text generation in dialogues using augmented data to prove formal definitions of equity in text generation and formal connections between human-likeness and learning equity. |
| Outcome: | The proposed model predicts relative-performance of multiple algorithms in generating equitable text as measured by human and automated evaluation. |