SMM4H-HeaRD 2025!
We are organizing SMM4H-HeaRD 2025! There are six challenging tasks with real data! Please register to join us!
Welcome
Hello! I am Takeshi Onishi, a postdoc at Cedars-Sinai working for medical NLP with Professor Gonzalez-Hernandez! I received my Ph.D. in Computer Science from Toyota Technological Institute at Chicago in 2020, advised by David McAllester. My undergraduate degree is a B.A. in Engineering from Toyota Technological Institute in Japan.
About me
My brief self-introduction.
Publications and talks
-
Political Bias of Large Language Models in Few-shot News Summarization.
Takeshi Onishi and James Caverlee.
Presented at International Workshop on Algorithmic Bias in Search and Recommendation at SIGIR, July 2024.
A collaborative research of Texas A&M University and Toyota Motor Corporation. -
Noisy-labeled Domain Adaptation under Generalized Label Shift
Kazuhiko Shinoda, Takeshi Onishi, Masashi Sugiyama.
In proceedings of the 37th Annual Conference of the Japanese Society for Artificial Intelligence, June 2023.
A collaborative research of the University of Tokyo and Toyota Motor Corporation. -
Dealing with Medication Non-Adherence Expressions in Twitter
Takeshi Onishi, Davy Weissenbacher, Ari Klein, Karen O’Connor and Graciela Gonzalez-Hernandez.
SMM4H at EMNLP 2018
-
Relation extraction with weakly supervised learning based on process-structure-property-performance reciprocity
Takeshi Onishi, Takuya Kadohira, Ikumu Watanabe.
Science and Technology of Advanced Materials, July 2018
The source code is available HERE. -
Emergent Predication Structure in Hidden State Vectors of Neural Readers
Hai Wang, Takeshi Onishi, Kevin Gimpel, David McAllester.
A Best Paper in Repl4NLP: 2nd Workshop on Representation Learning for NLP, August 2017
-
Who did What: A large-scale person-centered cloze dataset
Takeshi Onishi, Hai Wang, Mohit Bansal, Kevin Gimpel, and David McAllester.
In Proceedings of Empirical Methods in Natural Language Processing, Austin, Texas, November 2016
Activities
Here is my activities!
The First Japan-US Science Forum in Southern California "Frontiers in Science; Innovations in AI and Data Science"
We had The First Japan-US Science Forum in Southern California on February 22, with more than 70 people and 19 poster presentations! Thank you very much for joining us!
The poster award at The First Japan-US Science Forum in Southern California
I won the outstanding poster presentation award at The First Japan-US Science Forum in Southern California for “ToponymQA: Toponym Linking as multiple-choice QA by Retrieval-Augmented Generation.” This research will be published soon!
Frontiers in Science: Innovations in AI and Data Science (2/22)
I am excited to announce the first Japan-US Science Forum in Southern California on February 22!
This event will feature AI technologies and their applications in various research fields, including medicals, through guest talks, panel discussions, and poster sessions with researchers in Southern California. It is a fantastic opportunity to present your work and engage with individuals from different research fields.
Thanks to the support of JSPS and the UCLA Terasaki Center, no registration fee is required!
New paper has been published!
I’m excited to announce the publication of my latest paper: “Political Bias of Large Language Models in Few-Shot News Summarization.”
As Large Language Models(LLMs) continue to shape how we consume information, understanding their potential biases is more crucial than ever. In this work, we dive into the LLM’s political bias in the context of news summarization!
This is my collaborative research between Toyota Motor Corporation and Texas A&M University! Big thanks to everyone who supported and collaborated on this journey!