Communicative-Function-Based Sentence Classification for Construction of an Academic Formulaic Expression Database

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 3476–3497 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 3476 Communicative-Function-Based Sentence Classification for Construction of an Academic Formulaic Expression Database Kenichi Iwatsuki1 1The University of Tokyo iwatsuki@nii.ac.jp Akiko Aizawa21 2National Institute of Informatics aizawa@nii.ac.jp Abstract Formulaic expressions (FEs), such as ‘in this paper, we propose’ are frequently used in sci- entific papers. FEs convey a communicative function (CF), i.e. ‘showing the aim of the paper’ in the above-mentioned example. Al- though CF-labelled FEs are helpful in assist- ing academic writing, the construction of FE databases requires manual labour for assign- ing CF labels. In this study, we considered a fully automated construction of a CF-labelled FE database using the top–down approach, in which the CF labels are first assigned to sen- tences, and then the FEs are extracted. For the CF-label assignment, we created a CF-labelled sentence dataset, on which we trained a SciB- ERT classifier. We show that the classifier and dataset can be used to construct FE databases of disciplines that are different from the train- ing data. The accuracy of in-disciplinary clas- sification was more than 80%, while cross- disciplinary classification also worked well. We also propose an FE extraction method, which was applied to the CF-labelled sen- tences. Finally, we constructed and published a new, large CF-labelled FE database. The evaluation of the final CF-labelled FE database showed that approximately 65% of the FEs are correct and useful, which is sufficiently high considering practical use. 1 Introduction Formulaic expressions (FEs), such as ‘in this paper we propose’, are a type of multi-word expressions and are repeatedly used in scientific papers. Some FEs convey a communicative function (CF) of a sentence, which represents intentions of authors. For example, ‘in this paper, we propose’ conveys the CF of ‘showing the aim of the paper’. Databases comprising CF-labelled FEs are re- quired from a pedagogical perspective (Martinez and Schmitt, 2012), and a computer-based aca- Sentences Spatial meaning plays an important role in grounding information. Spatial meaning plays an important role in grounding information. (CF: Showing the importance of the topic) Sentences + CF FE: plays an important role in (CF: Showing the importance of the topic) FE + CF CF labelling FE extraction Figure 1: Process of creating FE database. demic writing assistance system1 that uses such CF-labelled FEs has been proposed (Mizumoto et al., 2017). Several attempts have been made to extract FEs from scientific corpora and categorise them based on CFs (Cortes, 2013; ¨Adel, 2014; Mizumoto et al., 2017; Morley, n. d.; Simpson- Vlach and Ellis, 2010; Lu et al., 2018). A CF- labelled FE database can be constructed using two main approaches: top–down and bottom–up ap- proaches (Biber et al., 2007; Durrant and Mathews- Aydınlı, 2011). By using the top–down approach, sentences are first assigned CF labels, and then FEs are extracted, while in the case of the bottom– up approach, FEs are first extracted and then …

Content truncated to 500 words