Alert button
Picture for Ryo Takahashi

Ryo Takahashi

Alert button

Are Prompt-based Models Clueless?

May 20, 2022
Pride Kavumba, Ryo Takahashi, Yusuke Oda

Figure 1 for Are Prompt-based Models Clueless?
Figure 2 for Are Prompt-based Models Clueless?
Figure 3 for Are Prompt-based Models Clueless?
Figure 4 for Are Prompt-based Models Clueless?
Viaarxiv icon

Two Training Strategies for Improving Relation Extraction over Universal Graph

Feb 12, 2021
Qin Dai, Naoya Inoue, Ryo Takahashi, Kentaro Inui

Figure 1 for Two Training Strategies for Improving Relation Extraction over Universal Graph
Figure 2 for Two Training Strategies for Improving Relation Extraction over Universal Graph
Figure 3 for Two Training Strategies for Improving Relation Extraction over Universal Graph
Figure 4 for Two Training Strategies for Improving Relation Extraction over Universal Graph
Viaarxiv icon

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

Jan 01, 2021
Sewon Min, Jordan Boyd-Graber, Chris Alberti, Danqi Chen, Eunsol Choi, Michael Collins, Kelvin Guu, Hannaneh Hajishirzi, Kenton Lee, Jennimaria Palomaki, Colin Raffel, Adam Roberts, Tom Kwiatkowski, Patrick Lewis, Yuxiang Wu, Heinrich Küttler, Linqing Liu, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel, Sohee Yang, Minjoon Seo, Gautier Izacard, Fabio Petroni, Lucas Hosseini, Nicola De Cao, Edouard Grave, Ikuya Yamada, Sonse Shimaoka, Masatoshi Suzuki, Shumpei Miyawaki, Shun Sato, Ryo Takahashi, Jun Suzuki, Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz, Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao, Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Wen-tau Yih

Figure 1 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Figure 2 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Figure 3 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Figure 4 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Viaarxiv icon

An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution

Nov 04, 2020
Ryuto Konno, Yuichiroh Matsubayashi, Shun Kiyono, Hiroki Ouchi, Ryo Takahashi, Kentaro Inui

Figure 1 for An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution
Figure 2 for An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution
Figure 3 for An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution
Figure 4 for An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution
Viaarxiv icon

Modeling Event Salience in Narratives via Barthes' Cardinal Functions

Nov 03, 2020
Takaki Otake, Sho Yokoi, Naoya Inoue, Ryo Takahashi, Tatsuki Kuribayashi, Kentaro Inui

Figure 1 for Modeling Event Salience in Narratives via Barthes' Cardinal Functions
Figure 2 for Modeling Event Salience in Narratives via Barthes' Cardinal Functions
Figure 3 for Modeling Event Salience in Narratives via Barthes' Cardinal Functions
Figure 4 for Modeling Event Salience in Narratives via Barthes' Cardinal Functions
Viaarxiv icon

Word Rotator's Distance: Decomposing Vectors Gives Better Representations

Apr 30, 2020
Sho Yokoi, Ryo Takahashi, Reina Akama, Jun Suzuki, Kentaro Inui

Figure 1 for Word Rotator's Distance: Decomposing Vectors Gives Better Representations
Figure 2 for Word Rotator's Distance: Decomposing Vectors Gives Better Representations
Figure 3 for Word Rotator's Distance: Decomposing Vectors Gives Better Representations
Figure 4 for Word Rotator's Distance: Decomposing Vectors Gives Better Representations
Viaarxiv icon

Data Augmentation using Random Image Cropping and Patching for Deep CNNs

Nov 22, 2018
Ryo Takahashi, Takashi Matsubara, Kuniaki Uehara

Figure 1 for Data Augmentation using Random Image Cropping and Patching for Deep CNNs
Figure 2 for Data Augmentation using Random Image Cropping and Patching for Deep CNNs
Figure 3 for Data Augmentation using Random Image Cropping and Patching for Deep CNNs
Figure 4 for Data Augmentation using Random Image Cropping and Patching for Deep CNNs
Viaarxiv icon

Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder

May 24, 2018
Ryo Takahashi, Ran Tian, Kentaro Inui

Figure 1 for Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder
Figure 2 for Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder
Figure 3 for Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder
Figure 4 for Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder
Viaarxiv icon