Takeda-Sasano Lab.
Main: tsukagoshi.hayato[at]gmail.com
Research: research.tsukagoshi.hayato[at]gmail.com
Education
April 2023 -
Doctor's degree, Department of Intelligent Systems, Graduate School of Informatics, Nagoya University, Japan
April 2021 - March 2023
Master's degree, Department of Intelligent Systems, Graduate School of Informatics, Nagoya University, Japan
April 2017 - March 2021
Bachelor's degree, Department of Computer Science, School of Informatics, Nagoya University, Japan
GPA: 3.89/4.30
February 2019 - March 2019
Short-term study abroad at Monash University, Australia
Refereed Publications
ACL 2024 SRW
Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples
Soma Sato, Hayato Tsukagoshi, Ryohei Sasano, Koichi TakedaLREC-COLING 2024
WikiSplit++: Easy Data Refinement for Split and Rephrase
Hayato Tsukagoshi, Tsutomu Hirao, Makoto Morishita, Katsuki Chousa, Ryohei Sasano, Koichi TakedaEACL 2024 (Main)
Sentence Representations via Gaussian Embedding
Shohei Yoda, Hayato Tsukagoshi, Ryohei Sasano, Koichi Takeda自然言語処理 Vol.30 No.1
Sentence Embeddings using Definition Sentences
Best paper award
Hayato Tsukagoshi, Ryohei Sasano, Koichi Takeda*SEM 2022 acceptance rate: 61.5%
Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals
Hayato Tsukagoshi, Ryohei Sasano, Koichi TakedaACL-IJCNLP 2021 main conference acceptance rate: 21.3%
DefSent: Sentence Embeddings using Definition Sentences
Hayato Tsukagoshi, Ryohei Sasano, Koichi Takeda
Non-Refereed Publications
arXiv 2024
Ruri: Japanese General Text Embeddings
Hayato Tsukagoshi, Ryohei SasanoarXiv 2023
Japanese SimCSE Technical Report
Hayato Tsukagoshi, Ryohei Sasano, Koichi Takeda第256回 自然言語処理研究発表会
論文テキストを用いた化合物探索の漸進的効率化
塚越駿, 岩田 和樹, 花田 博幸, 笹野 遼平, 竹内 一郎, 魚住 信之, 有澤 美枝子言語処理学会第29回年次大会 (NLP2023)
ガウス埋め込みに基づく文表現生成
陽田翔平 (若手奨励賞), 塚越駿, 笹野遼平, 武田浩一言語処理学会第28回年次大会 (NLP2022)
自然言語推論と再現器を用いたSplit and Rephrase における生成文の品質向上
塚越駿, 平尾努, 森下睦, 帖佐克己, 笹野遼平, 武田浩一言語処理学会第27回年次大会 (NLP2021)
定義文を用いた文埋め込み構成法
塚越駿, 笹野遼平, 武田浩一
Internships / Employments
November 2023 - June 2024
Part-time Employee at Preferred Elements, Inc.
Research Engineer
July 2023 - June 2024
Internship / Part-time Employee at Preferred Networks, Inc.
Research Engineer
October 2022 - March 2023
June 2021 - March 2024
Research Assistant of Moonshot R&D project "Observation and interpretation AI based on prior knowledge"
ムーンショット型研究開発事業: 事前知識に基づく観察・解釈AI 研究アシスタント
August 2021 - September 2021
Research Internship at NTT CS Lab.
Natural Language Processing / Python
May 2021 - August 2021
Software Engineering Internship at Mercari Inc.
Machine Learning, Search / Go, Python
April 2021 - May 2021
Server-side Engineering Internship at pixiv Inc.
Novel team, Search System Engineer / Python, PHP
February 2021 - March 2021
Server-side Engineering Internship at Recruit Co., Ltd.
Search System Engineer / ElasticSearch, AES, Locust
June 2020 - June 2021
Writer for AI-SCHOLAR
March 2020
Server-side Engineering Internship at CyberAgent Inc.
Scala, Akka, AWS (ECS, DynamoDB Streams)
January 2020 - March 2020
Server-side Engineer at Ateam Inc.
Developed in-house management system / Rails, Vue.js
September 2019
Server-side Engineering Internship at TeamLab Inc.
Developed API using postal codes and geometrical information / Go, MySQL, AWS (Fargate)
April 2019 - November 2019
R&D Engineering Internship at TRYETING Inc.
Time series forecasting, denoising / Python, R
Activities
September 2024
Development of General Text Embedding Model for Japanese
Encouragement Award (23/182), Sponshor Award (PKSHA)
August 2024
August 2024
May 2024
December 2023
ACL2023読み会 at 名大
第15回 最先端NLP勉強会
April 2023
May 2023
April 2023 - present
March 2023
資源として見る実験プログラム
Oral presentation at JLR2023, which is a workshop of the 29th Annual Meeting of the Association for Natural Language Processing.
March 2023
埋め込みで論理演算!データを確率分布で表す確率埋め込みの最前線
Discuss probabilistic embeddings.
Feburary 2023
次世代のトランスフォーマーを目指して: 状態空間モデル S4 の発展
Discuss S4 sucsessors.
January 2023
BERT Classification Tutorial (BERTによるテキスト分類)
A tutorial, reference implementation of text classification using BERT in 2023
December 2022
歪んだ空間の使い方: 双曲埋め込み+深層学習の主要研究まとめと最新動向
Article for State of AI Guides. Discuss Hyperbolic Embeddings, which embed words in a hyperbolic space instead of a Euclidean space.
October 2022
単語を箱で表現!新たな埋め込み手法 Box Embedding を基礎から理解
Article for State of AI Guides. Discuss Box Embeddings, which represent words using a box instead of a vector.
October 2022
[輪講資料] Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space
Reading group material. Discuss Optimus, which is a pre-trained VAE-based language model.
October 2022
Simple-SimCSE
An easy-to-read, easy-to-use implementation of SimCSE, which is a simple contrastive sentence embedding method.
May 2022
[輪講資料] Language-agnostic BERT Sentence Embedding
Reading group material. Discuss LaBSE, which is a effective multilingual sentence embedding model.
April 2022 -
輪読会主催: MLPシリーズ 深層学習 改訂第2版
Study group organizer.
February 2022
[輪講資料] SimCSE: Simple Contrastive Learning of Sentence Embeddings
Reading group material. Discuss SimCSE, which is a very simple but effective State-of-the-Art sentence embedding method using a pre-trained language model and contrastive learning.
November 2021
人工知能学会 言語・音声理解と対話処理研究会(SLUD) 第93回研究会 「第12回対話システムシンポジウム」 国際会議報告(ACL-IJCNLP)
Introduction to ACL.
May 2021 - August 2021
ログデータと言語モデルを用いた同義語辞書の自動構築
Blog post. Software Engineer, Machine Learning, Search Internship at Mercari Inc.
February 2021 - March 2021
Amazon Elasticsearch Serviceへの移行にかかる調査とLocustを用いた負荷試験
Blog post. Server-side Engineering Internship at Recruit Inc.
March 2020
DynamoDB Streamsを用いたAkka Streamsによるキャッシュ処理の実装とDynalystでのインターン
Blog post. Server-side Engineering Internship at CyberAgent Inc.
Awards / Honors
April 2023 - March 2027
Japan Society for Promotion of Science (JSPS) Research Fellowship for Young Scientists (DC1)
200,000 yen / month + 1,000,000 yen / year
April 2023 - March 2026
Nagoya University Interdisciplinary Frontier Fellowship
180,000 yen / month + 250,000 yen / year
April 2022
名古屋大学大学院 情報学研究科 修士研究中間発表 優秀賞
異なる教師信号から構築した文ベクトルの比較と統合手法の提案
April 2021 - March 2022
JEES/Softbank AI Human Resource Development Scholarship 2021
1,000,000 yen / year
June 2020
Cyber Agent Backend Tuning Competition
1st place out of 20 competitors
Certificates
December 2020
Database Specialist Examination (DB)
April 2020
TOEFL iBT
72 (Reading: 24, Listening 14, Speaking 16, Writing 18)
January 2020
TOEIC
790 (Listening 395, Reading 395)
December 2019
Applied Information Technology Engineer Examination (AP)