Tongnian Wang


2023

pdf
BabyStories: Can Reinforcement Learning Teach Baby Language Models to Write Better Stories?
Xingmeng Zhao | Tongnian Wang | Sheri Osborn | Anthony Rios
Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning

pdf
UTSA-NLP at RadSum23: Multi-modal Retrieval-Based Chest X-Ray Report Summarization
Tongnian Wang | Xingmeng Zhao | Anthony Rios
The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks

Radiology report summarization aims to automatically provide concise summaries of radiology findings, reducing time and errors in manual summaries. However, current methods solely summarize the text, which overlooks critical details in the images. Unfortunately, directly using the images in a multimodal model is difficult. Multimodal models are susceptible to overfitting due to their increased capacity, and modalities tend to overfit and generalize at different rates. Thus, we propose a novel retrieval-based approach that uses image similarities to generate additional text features. We further employ few-shot with chain-of-thought and ensemble techniques to boost performance. Overall, our method achieves state-of-the-art performance in the F1RadGraph score, which measures the factual correctness of summaries. We rank second place in both MIMIC-CXR and MIMIC-III hidden tests among 11 teams.