Using Formulaic Expressions in Writing Assistance Systems

Proceedings of the 27th International Conference on Computational Linguistics, pages 2678–2689 Santa Fe, New Mexico, USA, August 20-26, 2018. 2678 Using Formulaic Expressions in Writing Assistance Systems Kenichi Iwatsuki† †The University of Tokyo 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan iwatsuki@nii.ac.jp Akiko Aizawa‡† ‡National Institute of Informatics 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo, Japan aizawa@nii.ac.jp Abstract Formulaic expressions (FEs) used in scholarly papers, such as ‘there has been little discussion about’, are helpful for non-native English speakers. However, it is time-consuming for users to manually search for an appropriate expression every time they want to consult FE dictionaries. For this reason, we tackle the task of semantic searches of FE dictionaries. At the start of our research, we identified two salient difficulties in this task. First, the paucity of example sentences in existing FE dictionaries results in a shortage of context information, which is necessary for acquiring semantic representation of FEs. Second, while a semantic category label is assigned to each FE in many FE dictionaries, it is difficult to predict the labels from user input, forcing users to manually designate the semantic category when searching. To address these difficulties, we propose a new framework for semantic searches of FEs and propose a new method to lever- age both existing dictionaries and domain sentence corpora. Further, we expand an existing FE dictionary to consider building a more comprehensive and domain-specific FE dictionary and to verify the effectiveness of our method. Title and Abstract in Japanese 執筆支援システムにおける定型表現の利用 論文中に用いられる定型表現（formulaic expressions）とは，例えば‘there has been little discussion about’などであり，非英語母語話者の英語論文執筆に有益である。しかしな がら，定型表現辞書をその都度参照して適切な表現を探すのは容易ではない。そこで 本研究では，計算機による定型表現辞書の意味検索に取り組む。まず，本タスクにお ける課題として以下の2つを挙げる。既存の定型表現辞書に収録されている例文が少 なく意味表現の獲得に必要な文脈情報が不足していること，多くの定型表現辞書では 意味カテゴリごとに定型表現が分類されているが，ユーザの入力から意味カテゴリを 予測することが困難であり，ユーザに意味カテゴリを明示する手間が発生することで ある。 これらの課題を解決するため，本研究では定型表現の意味検索の新たな枠組み を提案し，既存の定型表現辞書を分野毎の英文コーパスと対応づけて利用するための 手法を提案する。 さらに，既存の定型表現辞書を拡張し，より網羅性が高く，かつ分 野特化型の定型表現辞書の構築を検討し，有効性を検証する。 1 Introduction Non-native English speakers writing scholarly papers often use the same expressions repeatedly or are not confident in the correctness of their usage of certain wording. Existing computer-based writing assistance systems do not always help them find better expressions than those they already know because such systems search a corpus by using simple pattern-matching based on input keywords (Chang et al., 2015; Chang and Chang, 2015; Jeong et al., 2014; Liu et al., 2016; Mizumoto et al., 2017). For instance, when a user wants to write about previous work and find expressions other than ‘little research was done This work is licenced under a Creative Commons Attribution 4.0 International Licence. Licence details: http: //creativecommons.org/licenses/by/4.0/ 2679 on’, the only one the user might know, a keyword-based search does not present expressions such as ‘there has been little discussion about’ to the user. A reasonable solution is using dictionaries of formulaic expressions (FEs) (Ellis et al., 2008; Conklin and Schmitt, 2008). FEs used in scholarly papers are helpful for non-native English speakers writing papers in English (Peters and Pauwels, 2015). FEs have a communicative function and thus in FE dictionaries, they are classified into categories on the basis of their functions. Consequently, if a user wants to write about the fact that there is little research on a topic, the user goes to the category ‘to show lack of existing research’ and finds expressions such as ‘there has been little …

Content truncated to 500 words