Doctoral candidate Ana Lucic successfully defended her dissertation, "Automatically Identifying Facet Roles from Comparative Structures to Support Biomedical Text Summarization," on November 17.
Her committee includes Associate Professor Catherine Blake, Associate Professor Roxanna Corina Girju (Linguistics), Associate Professor Miles Efron, Professor and Dean Allen Renear, and Professor J. Stephen Downie.
Abstract: Within the context of the articles in biomedical scholarly articles, comparison sentences represent a rhetorical structure commonly used to communicate findings. More generally, comparison sentences are rich with information about how the properties of one or more entities relate to one another. So far, in the biomedical domain, the emphasis has been on the recognition of comparative sentences in the text. This dissertation goes beyond sentence-level recognition and aims to automate the identification of the integral parts of a comparison sentence which are called comparative facets. The work uses the comparative facets from the Claim Framework (Blake, 2010) to identify direct comparisons that contain at least two compared entities, the basis of comparison (the endpoint) and communicate the result. Identifying comparison facets—the main contribution of this work—is a crucial step in the process of generating a comparative summary which constitutes the ultimate goal of this project.