Discourse-level Natural Language Understanding for Scientific Literature

Explore discourse-level natural language understanding for scientific literature in this 45-minute conference talk from the Computational Genomics Summer Institute (CGSI) 2022. Delve into cutting-edge research on scientific discourse tagging, evidence extraction, and biomedical experiment method classification. Learn about paragraph-level multi-task learning models for scientific fact-verification and cross-sentence n-ary relation extraction using graph LSTMs. Gain insights from related papers, including work on the MELINDA multimodal dataset and advanced techniques for analyzing scientific texts. Discover how these approaches can enhance comprehension and analysis of complex scientific literature across various domains.

Nanyun Violet Peng | Discourse-level Natural Language Understanding for Scientific Li... | CGSI 2022