In Layman’s Terms: Semi-Open Relation Extraction from Scientific Texts

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1489–1500 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 1489 In Layman’s Terms: Semi-Open Relation Extraction from Scientific Texts Ruben Kruiper∗, Julian F.V. Vincent, Jessica Chen-Burger, Marc P.Y. Desmulliez, Ioannis Konstas Heriot-Watt University Riccarton Campus, EH14 4AS Edinburgh, United Kingdom ∗Corresponding author: rk22@hw.ac.uk Abstract Information Extraction (IE) from scientific texts can be used to guide readers to the central information in scientific documents. But nar- row IE systems extract only a fraction of the information captured, and Open IE systems do not perform well on the long and complex sen- tences encountered in scientific texts. In this work we combine the output of both types of systems to achieve Semi-Open Relation Ex- traction, a new task that we explore in the Bi- ology domain. First, we present the Focused Open Biological Information Extraction (FO- BIE) dataset and use FOBIE to train a state-of- the-art narrow scientific IE system to extract trade-off relations and arguments that are cen- tral to biology texts. We then run both the nar- row IE system and a state-of-the-art Open IE system on a corpus of 10k open-access scien- tific biological texts. We show that a signifi- cant amount (65%) of erroneous and uninfor- mative Open IE extractions can be filtered us- ing narrow IE extractions. Furthermore, we show that the retained extractions are signifi- cantly more often informative to a reader.1 1 Introduction Identifying the central theme and concepts in sci- entific texts is a time-consuming task for experts and a hard task for laymen (Alper et al., 2004; El- Arini and Guestrin, 2011; Pain, 2016). This prob- lem is even more pronounced in inter-disciplinary fields of study, where experts in a target domain often lack the deeper knowledge of a source do- main (Carr et al., 2018). A specific example is biomimetics, an engineering problem-solving pro- cess in which one draws on analogous biological solutions (Kruiper et al., 2016). A major issue is that engineers (target domain) know little biol- ogy (source domain) or characteristics of plants or 1We release FOBIE and code at https://github. com/rubenkruiper/FOBIE. Figure 1: Example of Semi-Open Relation Extraction in the Biology domain (Burgess et al., 2006). We first extract the TRADE-OFF expressed between the central concepts ‘safety’ and ‘efficiency’ (in blue), that takes place specifically in ‘conifer species’ (in green). We further explore the content of a paper by investigating the results of an Open Information Extraction (OIE) system (in red). The central concepts captured by a TRADE-OFF mechanism enable the filtering of many irrelevant OIE extractions, which are found to be error- prone in scientific texts. Further OIE extractions found in the document can shed light on the semantic mean- ing of relevant concepts, e.g., ‘xylem’, as depicted at the top of the Figure (in the red box). animals (Vattam and Goel, 2013). This domain- mismatch complicates searching for and reason- ing over relevant scientific information, rendering biomimetics adventitious and solutions serendipi- tous …

Content truncated to 500 words