Slide 6
Slide 6 text
研究トピック抜粋
6
• ⾃然⾔語の表現学習
− Reina Akama, Kento Watanabe, Sho Yokoi, Sosuke Kobayashi,
Kentaro Inui. Unsupervised Learning of Style-sensitive Word
Vectors. ACL 2018.
− Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro Inui.
Attention Module is Not Only a Weight: Analyzing Transformers
with Vector Norms. EMNLP 2020.
− Masahiro Naito, Sho Yokoi, Geewook Kim, Hidetoshi Shimodaira.
Revisiting Additive Compositionality: AND, OR and NOT Operations
with Word Embeddings. ACL-SRW 2021.
• 最適輸送 for ⾃然⾔語処理
− Sho Yokoi, Ryo Takahashi, Reina Akama, Jun Suzuki, Kentaro Inui.
Word Rotatorʼs Distance. EMNLP 2020.
− Ayato Toyokuni, Sho Yokoi, Hisashi Kashima, Makoto Yamada.
Computationally Efficient Wasserstein Loss for Structured Labels.
EACL-SRW 2021.