Shengli Song — accepted AI-conference papers

2024

Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA

Chengen Lai, Shengli Song, Shiqi Meng, Jingyang Li, Sitong Yan, Guangneng Hu

AAAI 2024technical

Natural language explanation in visual question answer (VQA-NLE) aims to explain the decision-making process of models by generating natural language sentences to increase users' trust in the black-box systems. Existing post-hoc methods have achieved significant progress in obtaining a plausible exp…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2023

TITAN : Task-oriented Dialogues with Mixed-Initiative Interactions

Sitong Yan, Shengli Song, Jingyang Li, Shiqi Meng, Guangneng Hu

IJCAI 2023poster

In multi-domain task-oriented dialogue systems, users proactively propose a series of domain-specific requests that can often be under-or over-specified, sometimes with ambiguous and cross-domain demands. System-sided initiative would be necessary to identify certain situations and appropriately int…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗