The Robotic Surgery Procedural Framebank

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 3950–3959 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 3950 The Robotic Surgery Procedural Framebank Marco Bombieri1, Marco Rospocher2, Simone Paolo Ponzetto3, Paolo Fiorini1 1Department of Computer Science, University of Verona (Italy), 2Department of Foreign Languages and Literatures, University of Verona (Italy) 3Data and Web Science Group, University of Mannheim (Germany) {marco.bombieri 01, marco.rospocher, paolo.fiorini}@univr.it, simone@informatik.uni-mannheim. Abstract Robot-Assisted minimally invasive surgery is the gold standard for the surgical treatment of many pathological conditions, and several manuals and academic papers describe how to perform these interventions. These high-quality, often peer-reviewed texts are the main study resource for medical personnel and consequently contain essential procedural domain-specific knowledge. The procedural knowledge therein described could be extracted, e.g., on the basis of semantic parsing models, and used to develop clinical decision support systems or even automation methods for some procedure’s steps. However, natural language understanding algorithms such as, for instance, semantic role labelers have lower efficacy and coverage issues when applied to domain others than those they are typically trained on (i.e., newswire text). To overcome this problem, starting from PropBank frames, we propose a new linguistic resource specific to the robotic-surgery domain, named Robotic Surgery Procedural Framebank (RSPF). We extract from robotic-surgical texts verbs and nouns that describe surgical actions and extend PropBank frames by adding any of new lemmas, frames or role sets required to cover missing lemmas, specific frames describing the surgical significance, or new semantic roles used in procedural surgical language. Our resource is publicly available and can be used to annotate corpora in the surgical domain to train and evaluate Semantic Role Labeling (SRL) systems in a challenging fine-grained domain setting. Keywords: semantic role labeling, robotic-assisted surgical procedures, annotated dataset 1. Introduction Surgical practice has steadily improved in recent decades thanks to the constant support of the ap- proaches made available by observational science. Ex- amples of these approaches can be found in the rigor- ous methodologies employed in the research and de- velopment of new clinical protocols, drugs or surgi- cal instruments. To further support this constant im- provement, it was necessary to introduce the so-called Electronic Health Records (EHR) and hand-written op- erative notes in the operating theatres, which led to the proliferation of electronic documents concerning operational notes and clinical cases written in natural language (Wang et al., 2013). These reports are very schematic and concise in form and language, and they are targeting expert clinician, highlighting particular cases or anomalies that occurred during the surgery. However, in practice they are often written by medi- cal trainees and missing essential details (Nyamulani and Mulwafu, 2018). Academic papers, online tuto- rials, and robotic surgery textbooks are also continu- ously being published and peer-reviewed. Compared to EHR, these resources present the procedure more organically, with a less schematic and more detailed prose-style treatment (Bombieri et al., 2021). These types of texts are very valuable resources because they encode the so-called …

Content truncated to 500 words