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

Add to Chrome

Add to Firefox

Picture for Akari Asai

Akari Asai

When Not to Trust Language Models: Investigating Effectiveness and Limitations of Parametric and Non-Parametric Memories

Dec 20, 2022
Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Hannaneh Hajishirzi, Daniel Khashabi

Figure 1 for When Not to Trust Language Models: Investigating Effectiveness and Limitations of Parametric and Non-Parametric Memories

Figure 2 for When Not to Trust Language Models: Investigating Effectiveness and Limitations of Parametric and Non-Parametric Memories

Figure 3 for When Not to Trust Language Models: Investigating Effectiveness and Limitations of Parametric and Non-Parametric Memories

Figure 4 for When Not to Trust Language Models: Investigating Effectiveness and Limitations of Parametric and Non-Parametric Memories

* Code and data available at https://github.com/AlexTMallen/adaptive-retrieval; work in progress

Access Paper or Ask Questions

Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources

Nov 28, 2022
Xinyan Velocity Yu, Akari Asai, Trina Chatterjee, Junjie Hu, Eunsol Choi

Figure 1 for Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources

Figure 2 for Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources

Figure 3 for Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources

Figure 4 for Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources

* Accepted to Findings of EMNLP 2022. You can view our annotations, contribute to our survey, and view the analysis visualizations on our website at https://multilingual-dataset-survey.github.io

Access Paper or Ask Questions

RealTime QA: What's the Answer Right Now?

Jul 27, 2022
Jungo Kasai, Keisuke Sakaguchi, Yoichi Takahashi, Ronan Le Bras, Akari Asai, Xinyan Yu, Dragomir Radev, Noah A. Smith, Yejin Choi, Kentaro Inui

Figure 1 for RealTime QA: What's the Answer Right Now?

Figure 2 for RealTime QA: What's the Answer Right Now?

Figure 3 for RealTime QA: What's the Answer Right Now?

Figure 4 for RealTime QA: What's the Answer Right Now?

* RealTime QA Website: https://realtimeqa.github.io/

Access Paper or Ask Questions

MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages

Jul 02, 2022
Akari Asai, Shayne Longpre, Jungo Kasai, Chia-Hsuan Lee, Rui Zhang, Junjie Hu, Ikuya Yamada, Jonathan H. Clark, Eunsol Choi

Figure 1 for MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages

Figure 2 for MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages

Figure 3 for MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages

Figure 4 for MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages

* NAACL Workshop on Multilingual Information Access

Access Paper or Ask Questions

Attentional Mixtures of Soft Prompt Tuning for Parameter-efficient Multi-task Knowledge Sharing

May 24, 2022
Akari Asai, Mohammadreza Salehi, Matthew E. Peters, Hannaneh Hajishirzi

Figure 1 for Attentional Mixtures of Soft Prompt Tuning for Parameter-efficient Multi-task Knowledge Sharing

Figure 2 for Attentional Mixtures of Soft Prompt Tuning for Parameter-efficient Multi-task Knowledge Sharing

Figure 3 for Attentional Mixtures of Soft Prompt Tuning for Parameter-efficient Multi-task Knowledge Sharing

Figure 4 for Attentional Mixtures of Soft Prompt Tuning for Parameter-efficient Multi-task Knowledge Sharing

* 18 pages; 8 gigures. Preprint

Access Paper or Ask Questions

One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval

Jul 26, 2021
Akari Asai, Xinyan Yu, Jungo Kasai, Hannaneh Hajishirzi

Figure 1 for One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval

Figure 2 for One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval

Figure 3 for One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval

Figure 4 for One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval

* Our code and trained model are publicly available at https://github.com/AkariAsai/CORA

Access Paper or Ask Questions