[1T3-GS-6] Language media processing

[1T3-GS-6-03] L1 Vocabulary 3D Map (L1 Map): A Visual Map of L1 Word Relations in English through Word Embedding

Development and Verification using Elementary School-Level English Words for Learners in Japan

〇Jun Kaneko¹, Takashi Otsuki², Takayuki Sakaguchi³, Jesse Sokolovsky⁴ (1. Mie University Faculty of Education, 2. Yamagata University Graduate School of Science and Engineering, 3. Yamagata University Faculty of Education, Art and Science, 4. Mie University Center for General Education)

[[Online]]

Keywords:Word Embedding, Word2vec, fastText, English Education, Word Vectors

Achieving native-speaker proficiency is a formidable task for language learners. What can be done to draw closer to a native-speaker’s own sense of language? The present project attempted to provide one answer to that question through the creation of an L1 vocabulary 3D map, referred to below as L1 Map, which shows the relationships between words in visual form. A set of 185 words was drawn from the elementary school-level English textbook Let’s Try! 1. Each word in the set was associated with added-word vectors with 300 dimensions from the pretrained model for English, fastText, a library for the learning of word embeddings. To make L1 Map useable as a visual tool for learning, the 300 dimensions in these word vectors were reduced to three dimensions using UMAP (Uniform Manifold Approximation and Projection for Dimension Reduction). K-means clustering analysis was performed on the data with three dimensions. The results indicate that L1 Map may be a useful tool for learners of English. Additionally, L1 Map turns fastText’s inability to distinguish between multiple meanings into a strength, offering visualizations of word origins.