呉雅婷（ゴガテイ）

研究分野

• 文章内の各文の関連性（ディスコース関係）とその実用例について。例えば、簡略化された文章に詳細情報を付加することで、文章の理解しやすさを高める。
• 生成モデルを使い、単一言語話者と多言語話者の話すパターンを研究する。

大学

博士生(情報工学), 2022年8月から今まで

修士(情報工学), 2020年1月から今まで

テキサス大学オースティン校
指導教員：Jessy Li教授、 Alex Dimakis教授
研究室: UT NLP Group、 Wireless Networking and Communications Group(WNCG)

学部生(情報工学), 2014年9月 - 2019年7月

学部生(日本語), 2014年9月 - 2019年7月

大連理工大学

交換留学生(学部生、電子情報工学), 2017年9月 - 2018年8月

東京大学
指導教員：山﨑俊彦教授、研究室：相澤山﨑研

発表文献

(^†は等しく貢献した)

• QUDeval: The Evaluation of Questions Under Discussion Discourse Parsing [data]
  Yating Wu, Ritika Mangla, Greg Durrett and Junyi Jessy Li
  Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023, to appear. (査読あり)

• Elaborative Simplification as Implicit Questions Under Discussion [code and data]
  Yating Wu^†, William Sheffield^†, Kyle Mahowald, and Junyi Jessy Li
  Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023, to appear. (査読あり)

• Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion [code]
  Wei-Jen Ko, Yating Wu, Cutter Dalton, Dananjay Srinivas, Greg Durrett and Junyi Jessy Li
  Findings of the Association for Computational Linguistics (ACL), 2023, appeared. (査読あり)

• longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks [bib]
  Venelin Kovatchev, Trina Chatterjee, Venkata S Govindarajan, Jifan Chen, Eunsol Choi, Gabriella Chronis, Anubrata Das, Katrin Erk, Matthew Lease, Junyi Jessy Li, Yating Wu and Kyle Mahowald
  In Proceedings of the First Workshop on Dynamic Adversarial Data Collection (DADC) at the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), pages 41--52, 2022. (査読あり)
  

経歴

業界経歴

• Amazon Prime Video, 2023年6月 - 2023年8月(9週間)
  Software Develop Engineer Intern(received strong return incline).
  
  • Implemented an in-game notification system using a Rule Engine.
  • Set up Lambda to respond to external service notifications and fetch updates through API.
  • Designed a rule config table to store rules.
  • Automated the evaluation and execution of rules with Java Rule Engine.
  • Achieved two of three strech goals beside base logic within 9 weeks internship.

• Amazon Prime Video, 2021年6月 - 2021年9月(12週間)
  Software Develop Engineer Intern(received return offer). [実現したものは公式サイトに採用される]
  
  • Implemented a Ranking System for ranking the events based on its popularity. I wrote over 10,000 lines java code and assured over 97% coverage.
  • Designed and Implemented a Ranking Data DynamoDB table for saving viewership data and filter events.
  • Set up Lambda to automatically pulling and putting latest information to Database.
  • Contributed to the main team repository to sort events based on viewership data.
  • Ingested with inner service to create two new carousals to provide this service for new customers.

授業助手経歴

• University of Texas at Austin, 2021年9月から今まで
  CS391L: Machine Learning(TA)
  • Hold office hours and prepare materials for CS391L. It is a graduate level course for machine learning. 授業担当: Adam Klivans, Qiang Liu.
  
  
• University of Texas at Austin, 2020年5月 - 2021年5月
  EE422C: Software Design & Implementation II(TA)
  
  • Hold Recitations and office hours for EE422C Software Design & Implementation II. It is a course teaching Java Data Structures and Algorithm Analysis. 授業担当: Vallath Nandakumar, Edison Thomaz.

その他

• VMWare Codehouse Palo Alto 一等賞, 2021年7月[報道]
• 優秀卒業生, 2019年7月

リンク

Department of Electrical and Computer Engineering

The University of Texas at Austin

The University of Tokyo

---