@inproceedings{494843b22ef045b994ed4f6ca2ac2dfc,
title = "An Assessment of Substitute Words in the Context of Academic Writing Proposed by Pre-trained and Specific Word Embedding Models",
abstract = "Researchers who are non-native speakers of English always face some problems when composing scientific articles in this language. Most of the time, it is due to lack of vocabulary or knowledge of alternate ways of expression. In this paper, we suggest to use word embeddings to look for substitute words used for academic writing in a specific domain. Word embeddings may not only contain semantically similar words but also other words with similar word vectors, that could be better expressions. A word embedding model trained on a collection of academic articles in a specific domain might suggest similar expressions that comply to that writing style and are suited to that domain. Our experiment results show that a word embedding model trained on the NLP domain is able to propose possible substitutes that could be used to replace the target words in a certain context.",
keywords = "Academic writing, Dictionary lookup, Synonym, Word embedding, Word similarity",
author = "Goh, {Chooi Ling} and Yves Lepage",
note = "Funding Information: This work was supported by JSPS KAKENHI Grant Number JP18K11446. Publisher Copyright: {\textcopyright} 2020, Springer Nature Singapore Pte Ltd.; 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019 ; Conference date: 11-10-2019 Through 13-10-2019",
year = "2020",
doi = "10.1007/978-981-15-6168-9_34",
language = "English",
isbn = "9789811561672",
series = "Communications in Computer and Information Science",
publisher = "Springer",
pages = "414--427",
editor = "Le-Minh Nguyen and Satoshi Tojo and Xuan-Hieu Phan and K{\^o}iti Hasida",
booktitle = "Computational Linguistics - 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers",
}