Publications
2023
Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi
Self-RAG: Learning to Retrieve, Generate and Critique through Self-Reflections
NeurIPS Workshop on Instruction Tuning and Instruction Following (Non Archival), 2023.
[Paper] / [Website] / [Code] / [Model checkpoint]Jungo Kasai, Keisuke Sakaguchi, Yoichi Takahashi, Ronan Le Bras, Akari Asai, Xinyan Yu, Dragomir Radev, Noah A. Smith, Yejin Choi, Kentaro Inui
RealTime QA: What’s the Answer Right Now?
NeurIPS (Dataset and Benchmark Track), 2023.
[Paper] / [Website]Joongwon Kim, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi.
TaskWeb: Selecting Better Source Tasks for Multi-task NLP
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
[Paper]Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, Xilun Chen.
How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval
Findings of Empirical Methods in Natural Language Processing (EMNLP), 2023.
[Paper] / [Code]Odunayo Ogundepo, Tajuddeen R. Gwadabe, Clara E. Rivera, Jonathan H. Clark, Sebastian Ruder, David Ifeoluwa Adelani, Bonaventure F. P. Dossou, …, Akari Asai (52 authors).
AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages
Findings of Empirical Methods in Natural Language Processing (EMNLP), 2023.
[Paper] / [Website]Alex Mallen^, Akari Asai^, Victor Zhong, Rajarshi Das, Daniel Khashabi, Hannaneh Hajishirzi
When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
The Annual Conference of the Association for Computational Linguistics (ACL), 2023.
[Paper] / [Code]Akari Asai, Timo Schick, Patrick Lewis, Xilun Chen, Gautier Izacard, Sebastian Riedel, Hannaneh Hajishirzi, and Wen-tau Yih
Task-aware Retrieval with Instructions
Findings of The Annual Conference of the Association for Computational Linguistics (ACL), 2023.
[Paper] / [Code]Xiaoyu Shen, Akari Asai, Bill Byrne and Adria de Gispert
xPQA: Cross-Lingual Product Question Answering in 12 Languages
The Annual Conference of the Association for Computational Linguistics (ACL; Industry track), 2023.
2022
Akari Asai, Mohammadreza Salehi, Matthew E. Peters, Hannaneh Hajishirzi
Attentional Mixtures of Soft Prompt Tuning for Parameter-efficient Multi-task Knowledge Sharing
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.
[Paper] / [Code]Xinyan Yu-, Akari Asai-, Trina Chatterjee, Junjie Hu, Eunsol Choi
Beyond Counting Datasets: Investigating Multilingual Dataset Construction and Necessary Resources
Findings of Empirical Methods in Natural Language Processing (EMNLP), 2022.
[Paper]Akari Asai, Matt Gardner, and Hannaneh Hajishirzi
Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks
Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2022 (oral).
[Paper] / [Code]Akari Asai, Shayne Longpre, Jungo Kasai, Chia-Hsuan Lee, Rui Zhang, Junjie Hu, Ikuya Yamada, Jonathan H Clark, and Eunsol Choi
MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages
Workshop on Multilingual Information Access, 2022.
[Paper] / [Code] / [EvalAI Competition Site]
2021
Akari Asai, Xinyan Yu, Jungo Kasai, and Hannaneh Hajishirzi
One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval
Conference on Neural Information Processing Systems (NeurIPS), 2021.
[Paper] / [Code] / [Talk] / [Slides] / [Poster]Akari Asai, and Eunsol Choi
Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval
The Annual Conference of the Association for Computational Linguistics (ACL), 2021.
[Paper] / [Code] / [Poster] / [Slides]Ikuya Yamada, Akari Asai, and Hannaneh Hajishirzi
Efficient Passage Retrieval with Hashing for Open-domain Question Answering
The Annual Conference of the Association for Computational Linguistics (ACL), 2021.
[Paper] / [Code]Akari Asai, Jungo Kasai, Jonathan H. Clark, Kenton Lee, Eunsol Choi, and Hannaneh Hajishirzi
XOR QA: Cross-lingual Open-Retrieval Question Answering
Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2021 (oral).
[Project] / [Paper] / [Code] / [Poster] / [Slides]Alon Talmor, Ori Yoran, Amnon Catav, Dan Lahav, Yizhong Wang, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi, and Jonathan Berant
MultiModalQA: Complex Question Answering over Text, Tables and Images
International Conference on Learning Representations (ICLR), 2021.
[Project] / [OpenReview]
2020
Ikuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda, and Yuji Matsumoto
LUKE: Deep Contextualized Entity Representations withEntity-aware Self-attention
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020.
[Paper] / [Code] / [Video]Ikuya Yamada, Akari Asai, Jin Sakuma, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji, and Yuji Matsumoto.
Wikipedia2Vec: An Optimized Tool for Learning Embeddings of Words and Entities from Wikipedia
Conference on Empirical Methods in Natural Language Processing (EMNLP), system demonstrations, 2020.
[Paper] / [Code] / [Project]Akari Asai, and Hannaneh Hajishirzi
Logic-guided Data Augmentation and Regularization for Consistent Question Answering
The Annual Conference of the Association for Computational Linguistics (ACL), 2020.
[Paper] / [Code] / [Video]Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher, and Caiming Xiong
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
International Conference on Learning Representations (ICLR), 2020.
[Paper] / [OpenReview] / [Code] / [Slides] / [Video]
Publications before Ph.D.
Takumi Kawashima, Qing Yu, Akari Asai, Daiki Ikami, Kiyoharu Aizawa.
The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals
International Conference on Pattern Recognition (ICPR), 2020.
[Paper]Akari Asai, Ikami Daiki, and Kiyoharu Aizawa
Multi-task Learning based on Separable Formulation of Depth Estimation and its Uncertainty
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Uncertainty and Robustness in Deep Visual Learning, 2019.
[Paper] / [Poster]Akari Asai, Sara Evensen, Behzad Golshan, Alon Halevy, Vivian Li, Andrei Lopatenko, Daniela Stepanov, Yoshihiko Suhara, Wang-Chiew Tan, Yinzhan Xu
HappyDB: A Corpus of 100,000 Crowdsourced Happy Moments
International Conference on Language Resources and Evaluation (LREC), 2018.
[Project] / [Paper] / [Shared task at AAAI 2019] / [MIT Technology Review]Akari Asai, Vivian Li, Daniela Stepanov, and Wang-Chiew Tan
A Data-Driven Approach to Understanding Happiness
Widening NLP Workshop (WiNLP), 2017.
[Project] / [Paper]