Yoshitomo Matsubara

Applied Scientist at Amazon Alexa AI
Ph.D. in Computer Science

Information Retrieval / Question Answering


Building effective, efficient information retrieval (IR) systems is important and challenging, and such systems are indispensable for our daily lives. We need to be aware of latency, accuracy, contents, misinformation, and more. Information retrieval is also an essential component of question answering (QA) systems. Especially for Web-based QA systems, we retrieve relevant documents from tons of web articles by ranking them given a query, and extracting correct answers from such a large search space is challenging.

Related Publications

Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems

EMNLP 2022 (Findings)

Yoshitomo Matsubara, Luca Soldaini, Eric Lind, Alessandro Moschitti

This work was done while I was an applied science intern at Amazon Alexa AI.

Paper Amazon Science Preprint Code

COVIDLies: Detecting COVID-19 Misinformation on Social Media

EMNLP 2020 Workshop on NLP for COVID-19 (Part 2)

Best Paper Award
Tamanna Hossain*, Robert L Logan IV*, Arjuna Ugarte*, Yoshitomo Matsubara*, Sameer Singh, Sean Young

* First four authors contributed equally.

Paper OpenReview Demo

ZOTBOT: Using Reading Comprehension and Commonsense Reasoning in Conversational Agents

Alexa Prize 2019

William Schallock, Daniel Agress*, Yao Du*, Dheeru Dua*, Lyuyang Hu*, Yoshitomo Matsubara*, Sameer Singh

* Apart from the first and last authors, the authors are listed in alphabetical order.


Reranking for Efficient Transformer-based Answer Selection

SIGIR 2020

Yoshitomo Matsubara, Thuy Vu, Alessandro Moschitti

This work was done while I was an applied science intern at Amazon Alexa.

Paper Amazon Science Video