Lawrence Jiang's research while affiliated with Duke University and other places

Publications (4)

Article
Full-text available
The advent of patient access to complex medical information online has highlighted the need for simplification of biomedical text to improve patient understanding and engagement in taking ownership of their health. However, comprehension of biomedical text remains a difficult task due to the need for domain-specific expertise. We aimed to study the...
Article
Full-text available
Scientific research is driven by allocation of funding to different research projects based in part on the predicted scientific impact of the work. Data-driven algorithms can inform decision-making of scarce funding resources by identifying likely high-impact studies using bibliometrics. Compared to standardized citation-based metrics alone, we uti...
Preprint
Full-text available
Scientific research is propelled by allocation of funding to different research projects based in part on the predicted scientific impact of the work. Data-driven algorithms can inform decision-making of funding by identifying likely high-impact studies using bibliometrics. Compared to standardized citation-based metrics alone, we utilize a machine...
Preprint
Full-text available
We aimed to study the simplification of biomedical text via large language models (LLMs). Specifically, we finetuned three language models to perform substitutions of complex words and word phrases for their respective hypernym in biomedical definitions. This process was then evaluated by readability metrics, and two measures of sentence complexity...

Citations

... Dependency analysis. In this study, a method is utilized to quantify syntactic complexity across various text datasets by calculating the Mean Dependency Distance (MDD), a metric indicative of linguistic intricacy [51][52][53]. Utilizing the spaCy library, the MDD metric gauges the average number of words that separate a word from its syntactic head within a sentence. Specifically, the MDD is derived by parsing each sentence to identify these dependencies, calculating the absolute differences between the indices of each word and its head, and then averaging these distances across the entire text. ...