Embedding
「詞向量(word vector)」是將詞彙轉換成包含語意訊息的向量表達的技術。透過類神經網路訓練，將詞彙從 one-hot encoding 的高維度向量表達，轉換成低維度的向量，以利運算的進行。在向量空間中，cosine similarity 越高的兩個向量，也代表它們的語意越相近。
System Implementation
Under Construction…
Resources
Publications
- Jhih-Sheng Fan, Mu Yang, Peng-Hsuan Li, Wei-Yun Ma. “HWE: Word Embedding with Heterogeneous Features”. IEEE ICSC, Jan 2019.
- Chi-Yen Chen, Wei-Yun Ma. “Word Embedding Evaluation Datasets and Wikipedia Title Embedding for Chinese”. LREC, May 2018.
- Chi-Yen Chen, Wei-Yun Ma. “Embedding Wikipedia Title Based on Its Wikipedia Text and Categories”. IALP, Dec 2017.
Researchers and Developers
馬偉雲、王欣陽、薛祐婷、范植昇、楊慕、陳紀嫣