CONNER: A Cascade Count and Measurement Extraction Tool for Scientific Discourse

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 1239–1244 Bangkok, Thailand (online), August 5–6, 2021. ©2021 Association for Computational Linguistics 1239 Jarvis Lab at SemEval-MeasEval Task 8: A Cascade Count and Measurement Extraction Tool for Scientific Discourse Jiarun Cao, Yuejia Xiang, Yunyan Zhang, Zhiyuan Qi, Xi Chen∗, Yefeng Zheng Jarvis Lab, Tencent {jerrycjrcao,yuejiaxiang,yunyanzhang,jasonxchen, yefengzheng}@tencent.com,qizhyuan@gmail.com Abstract This paper presents our contribution to SemEval 2021 Task 8: MeasEval. The purpose of this task is identifying the counts and measurements from clinical scientific discourse, including quantities, entities, prop- erties, qualifiers, units, modifiers, and their mutual relations. This task can be induced to a joint entity and relation extraction problem. Accordingly, we propose CONNER, a cascade count and measurement extraction tool that can identify entities and the corresponding relations in a two-step pipeline model. We provide a detailed description of the pro- posed model hereinafter. Furthermore, the impact of the essential modules and our in-process technical schemes are also investi- gated. Our code is released and available at https://github.com/yuejiaxiang/ CONNER. 1 Introduction Clinicians are currently coping with a massive amount of information, both from raw experimen- tal data and scientific publications recording their results. However, the ever-expanding information sources have exceeded the ability of clinicians to digest and utilize them properly (Botsis et al., 2011; Cao et al., 2018; Zhou et al., 2010). Clinical information extraction tools (Zhang et al., 2020; De Bruijn et al., 2011; Li and Huang, 2016; Yehia et al., 2019; Mulyar and McInnes, 2020) in the text-mining field make an effort to alleviate the clinician’s burden according to exploit how to bet- ter utilize the knowledge contained in scientific discourse, accessible in the form of natural human language. Automating the process of understand- ing the relevant parts of the scientific literature allows for effective searching, and enabling infer- ence of new information and hypothesis generation for clinical research. ∗ Corresponding author Counts and measurements are an important part of information source from the scientific dis- course (Harper et al., 2021). However, extracting these count and measurement entities and their in- teractions is challenging, since the way scientists write them can be ambiguous and inconsistent, and the location of this information relative to the mea- surement can vary greatly. In this paper, we focus on the SemEval 2021 MeasEval task which is composed of five sub-tasks that cover span extraction, classification, and re- lation extraction. As shown in Figure 1 it firstly demands to identify all the quantity spans given a paragraph from a scientific text. For each iden- tified quantity, we need to extract the measured entity, measured property and qualifier which are corresponded to identified quantity. Besides, the relationships between quantity, measured entity, measured property and qualifier are also required to be identified. Lastly, the unit and type of the quantity is also needed to be recognized if they exist. However, some elements are only present for the largest bed inventory of 13 kg e.g., Ti, Cr, and Mn. However, all elements included within Fig. 5 …

Content truncated to 500 words