Zhuofu Tao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhuofu Tao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Eduard Hovy
Carnegie Mellon University
1 shared publication - Kevin Lu
University of Waterloo
1 shared publication - Malihe Alikhani
Northeastern University Boston MA USA
1 shared publication - Steven Y. Feng
Language Technologies Institute Carnegie Mellon University
1 shared publication - Teruko Mitamura
Language Technologies Institute Carnegie Mellon University
1 shared publication - Varun Gangal
Carnegie Mellon University
1 shared publication
Latest Publications
- Open Access
Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models
We investigate the use of multimodal information contained in images as an effective method for enhancing the commonsense of Transformer models for text generation. We perform experiments using BART and T5 on concept-to-text generation, specifically the task of generative commonsense reasoning, or CommonGen. We call our approach VisCTG: Visually Grounded Concept-to-Text Generation. VisCTG involves captioning images representing appropriate everyday scenarios, and using these captions to enrich and steer the generation process. Comprehensive evaluation and analysis demonstrate that VisCTG noticeably improves model performance while successfully addressing several issues of the baseline generations, including poor commonsense, fluency, and specificity.
Open AccessRetrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models
We investigate the use of multimodal information contained in images as an effective method for enhancing the commonsense of Transformer models for text generation. We perform experiments using BART and T5 on concept-to-text generation, specifically the task of generative commonsense reasoning, or CommonGen. We call our approach VisCTG: Visually Grounded Concept-to-Text Generation. VisCTG involves captioning images representing appropriate everyday scenarios, and using these captions to enrich and steer the generation process. Comprehensive evaluation and analysis demonstrate that VisCTG noticeably improves model performance while successfully addressing several issues of the baseline generations, including poor commonsense, fluency, and specificity.