Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Kazutoshi Shinoda

Kazutoshi Shinoda

Which Shortcut Solution Do Question Answering Models Prefer to Learn?

Nov 29, 2022
Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa

Figure 1 for Which Shortcut Solution Do Question Answering Models Prefer to Learn?

Figure 2 for Which Shortcut Solution Do Question Answering Models Prefer to Learn?

Figure 3 for Which Shortcut Solution Do Question Answering Models Prefer to Learn?

Figure 4 for Which Shortcut Solution Do Question Answering Models Prefer to Learn?

* Accepted to AAAI 2023

Access Paper or Ask Questions

Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering

Nov 29, 2022
Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa

Figure 1 for Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering

Figure 2 for Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering

Figure 3 for Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering

Figure 4 for Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering

* Accepted to the KnowledgeNLP workshop at AAAI 2023

Access Paper or Ask Questions

Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering

Oct 26, 2022
Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa

Figure 1 for Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering

Figure 2 for Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering

Figure 3 for Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering

Figure 4 for Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering

* Accepted to BlackboxNLP 2022

Access Paper or Ask Questions

Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap

Sep 23, 2021
Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa

Figure 1 for Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap

Figure 2 for Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap

Figure 3 for Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap

Figure 4 for Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap

* MRQA workshop at EMNLP 2021

Access Paper or Ask Questions

Variational Question-Answer Pair Generation for Machine Reading Comprehension

Apr 07, 2020
Kazutoshi Shinoda, Akiko Aizawa

Figure 1 for Variational Question-Answer Pair Generation for Machine Reading Comprehension

Figure 2 for Variational Question-Answer Pair Generation for Machine Reading Comprehension

Figure 3 for Variational Question-Answer Pair Generation for Machine Reading Comprehension

Figure 4 for Variational Question-Answer Pair Generation for Machine Reading Comprehension

Access Paper or Ask Questions