斉藤 いつみ

🚀 NLPコロキウム 

自然言語処理 31(1) 300-309 2024年  

How Well Do Vision Models Encode Diagram Attributes? 

ACL (Student Research Workshop) 564-575 2024年  

SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images. 

CoRR abs/2301.04883 2023年  

SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images. 

AAAI 13636-13645 2023年  

Japanese ASR-Robust Pre-trained Language Model with Pseudo-Error Sentences Generated by Grapheme-Phoneme Conversion. 

Interspeech 2022(INTERSPEECH) 2688-2692 2022年  

Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction. 

CoRR abs/2111.09029 2021年  

Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction. 

International Joint Conference on Neural Networks(IJCNN) 1-8 2021年  

Abstractive Summarization with Combination of Pre-trained Sequence-to-Sequence and Saliency Models. 

CoRR abs/2003.13028 2020年  

Unsupervised Domain Adaptation of Language Models for Reading Comprehension. 

Proceedings of The 12th Language Resources and Evaluation Conference(LREC) 5392-5399 2020年  

質問意図の明確化に着目した機械読解による質問応答手法の提案 

人工知能学会論文誌 34(5) A-J14_1-12 2019年9月1日  

Unsupervised Domain Adaptation of Language Models for Reading Comprehension. 

CoRR abs/1911.10768 2019年  

A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension. 

CoRR abs/1905.12848 2019年  

Generalized Large-Context Language Models Based on Forward-Backward Hierarchical Recurrent Encoder-Decoder Models. 

IEEE Automatic Speech Recognition and Understanding Workshop(ASRU) 554-561 2019年  

深層学習におけるアテンション技術の最新動向—Latest Trends of Attention Mechanisms in Deep Learning 

電子情報通信学会誌 = The journal of the Institute of Electronics, Information and Communication Engineers 101(6) 591-596 2018年6月  

Commonsense Knowledge Base Completion and Generation. 

Proceedings of the 22nd Conference on Computational Natural Language Learning(CoNLL) 141-150 2018年