Automatic Textual Evidence Mining in COVID-19 Literature
This system addresses the need for efficient evidence retrieval in life sciences, particularly for COVID-19 research, but is incremental as it builds on existing techniques for named entity recognition and information extraction.
The researchers tackled the problem of automatically mining textual evidence from COVID-19 literature by developing EVIDENCEMINER, a web-based system that retrieves evidence for user queries using novel data-driven methods, achieving fully automated operation without human annotation.
We created this EVIDENCEMINER system for automatic textual evidence mining in COVID-19 literature. EVIDENCEMINER is a web-based system that lets users query a natural language statement and automatically retrieves textual evidence from a background corpora for life sciences. It is constructed in a completely automated way without any human effort for training data annotation. EVIDENCEMINER is supported by novel data-driven methods for distantly supervised named entity recognition and open information extraction. The named entities and meta-patterns are pre-computed and indexed offline to support fast online evidence retrieval. The annotation results are also highlighted in the original document for better visualization. EVIDENCEMINER also includes analytic functionalities such as the most frequent entity and relation summarization.