Seungju Han

Generative Correlation Discovery Network for Multi-label Learning

2019

The goal of Multi-label learning is to predict multiple labels of each single instance. This is a challenging problem since the training data is limited, long-tail label distribution, and complicated label correlations. Generally, more training …

Understanding and Improving the Exemplar-based Generation for Open-domain Conversation

2021 · arXiv (Cornell University)

Exemplar-based generative models for open-domain conversation produce responses based on the exemplars provided by the retriever, taking advantage of generative models and retrieval models. However, they often ignore the retrieved exemplars while generating responses or …

Measuring and Improving Semantic Diversity of Dialogue Generation

2022 · arXiv (Cornell University)

Response diversity has become an important criterion for evaluating the quality of open-domain dialogue generation models. However, current evaluation metrics for response diversity often fail to capture the semantic diversity of generated responses, as they …