计算机科学
自然语言处理
人工智能
语义学(计算机科学)
领域(数学分析)
词汇
生物医学
语言理解
语言学
程序设计语言
数学分析
哲学
数学
生物
遗传学
作者
Benedikt Boecking,Naoto Usuyama,Shruthi Bannur,Daniel C. Castro,Anton Schwaighofer,Stephanie L. Hyland,Maria Teodora Wetscherek,Tristan Naumann,Aditya Nori,Javier Alvarez-Valle,Hoifung Poon,Ozan Oktay
标识
DOI:10.48550/arxiv.2204.09817
摘要
Multi-modal data abounds in biomedicine, such as radiology images and reports. Interpreting this data at scale is essential for improving clinical care and accelerating clinical research. Biomedical text with its complex semantics poses additional challenges in vision--language modelling compared to the general domain, and previous work has used insufficiently adapted models that lack domain-specific language understanding. In this paper, we show that principled textual semantic modelling can substantially improve contrastive learning in self-supervised vision--language processing. We release a language model that achieves state-of-the-art results in radiology natural language inference through its improved vocabulary and novel language pretraining objective leveraging semantics and discourse characteristics in radiology reports. Further, we propose a self-supervised joint vision--language approach with a focus on better text modelling. It establishes new state of the art results on a wide range of publicly available benchmarks, in part by leveraging our new domain-specific language model. We release a new dataset with locally-aligned phrase grounding annotations by radiologists to facilitate the study of complex semantic modelling in biomedical vision--language processing. A broad evaluation, including on this new dataset, shows that our contrastive learning approach, aided by textual-semantic modelling, outperforms prior methods in segmentation tasks, despite only using a global-alignment objective.
科研通智能强力驱动
Strongly Powered by AbleSci AI