CliMedBERT: A Pre-trained Language Model for Climate and Health-related Text
This work addresses the problem of inefficient knowledge synthesis for policymakers and researchers in climate and health, though it is incremental as it applies existing language modeling techniques to new domains.
The authors tackled the challenge of synthesizing vast, multidisciplinary climate and health science literature by developing CliMedBERT, a set of pre-trained language models for these domains, which can support tasks like concept similarity detection and policy text generation.
Climate change is threatening human health in unprecedented orders and many ways. These threats are expected to grow unless effective and evidence-based policies are developed and acted upon to minimize or eliminate them. Attaining such a task requires the highest degree of the flow of knowledge from science into policy. The multidisciplinary, location-specific, and vastness of published science makes it challenging to keep track of novel work in this area, as well as making the traditional knowledge synthesis methods inefficient in infusing science into policy. To this end, we consider developing multiple domain-specific language models (LMs) with different variations from Climate- and Health-related information, which can serve as a foundational step toward capturing available knowledge to enable solving different tasks, such as detecting similarities between climate- and health-related concepts, fact-checking, relation extraction, evidence of health effects to policy text generation, and more. To our knowledge, this is the first work that proposes developing multiple domain-specific language models for the considered domains. We will make the developed models, resources, and codebase available for the researchers.