Welcome! My name is Jiho (a.k.a. PJ and Park Ji Ho).
I am an engineer and researcher that builds products with machine learning.
I am currently working as a computational linguist for the Google Assistant NLP Team, based in Tokyo since January 2020.
I started machine learning by doing research in natural language processing (NLP), but I am interested in expanding to different domains like audio/speech, computer vision, recommender systems, etc.
My dream is to build a useful product with a great team.
I was born in Seoul, Korea but spent my 20s in Hong Kong. I studied at Korean Minjok Leadership Academy (KMLA; 민족사관고등학교) and Hong Kong University of Science and Technology (HKUST; B.Eng, M.Phil), majoring Computer Science.
keywords: sentiment/emotion analysis & abusive language in social media texts (twitter), representation learning, transfer learning, text classification
- Ji Ho Park (2018), Finding Good Representations of Emotions for Text Classification, M.Phil. Thesis, Hong Kong University of Science and Technology
- Ji Ho Park, Jamin Shin, Pascale Fung (2018), Reducing Gender Bias in Abusive Language Detection, In Proceedings of the EMNLP 2018, Brussels, Belgium
- Ji Ho Park, Peng Xu, Pascale Fung (2018), PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and# hashtags, In Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018) at NAACL-HLT 2019, New Orleans, USA (ranked Top-3 in all 5 subtasks)
- Ji Ho Park, Pascale Fung (2017) One-step and two-step classification for abusive language detection on twitter In Proceedings of the First Workshop on Abusive Language Online at ACL 2017, Vancouver, Canada
- Ji Ho Park, Nayeon Lee, Dario Bertero, Anik Dey, Pascale Fung (2017), Emojive! Collecting Emotion Data from Speech and Facial Expression Using Mobile Game App.Show-and-tell Session of Interspeech 2017
- Pascale Fung, Dario Bertero, Peng Xu, Ji Ho Park, Chien-Sheng Wu, Andrea Madotto (2018), Empathetic Dialog Systems, In Proceedings of the International Conference on Language Resources and Evaluation. European Language Resources Association (LREC)
- Peng Xu, Andrea Madotto, Chien-Sheng Wu, Ji Ho Park, Pascale Fung, (2018), Emo2vec: Learning generalized emotion representation by multi-task training. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA) at EMNLP 2018