Sean Chen 陳佑翔

你好,我是陳佑翔,資訊工程學系出身,熱衷於資料分析及嘗試新技術。碩士時期主要研究領域為深度學習、自然語言、推薦系統。並透過論文進一步探討基於附帶資訊的可解釋推薦系統 (e.g. 用戶評論、知識圖譜),除了提升預測效能也可提出推薦的依據。
目前待業中,希望能結合所學,從事資料科學家、機器學習工程師相關的工作。本身樂於結交新朋友,並參與過資訊相關競賽提升團隊合作經驗,於閒暇時喜歡看書、打球、健身。

  Taipei City, Taiwan |   |  


專業技能

Programming

  • Python (approx. 3 years experience. Mainly used) 
  • JAVA (Android) 
  • C#

Database / Analyst

  • MySQL (MariaDB, SQL Server)

  • Pandas

Deep Learning

  • Numpy

  • PyTorch

  • Scikit-Learn

  • Gensim

Model Development

Experience in machine learning development and optimization

  • SVM, Boosting, Regression model

  • CNN

  • Sequential model (e.g. RNN, LSTM, GRU)

  • Attention model

  • Transformers

  • BERT

Recommendation System

Strong experience in modeling user-item interaction.
Research heavily in :

  • Collaborative filtering
  • Matrix factorization
  • Click-through rate (CTR) prediction
  • Review-based recommendation system
  • Knowledge Graph-based recommendation system

工作經歷

專案研究助理  國立臺灣師範大學

九月 2018 - 七月 2020

開發思考力遊戲 app,思考力平台是評量創造力的遊戲測驗,包含一筆劃遊戲、屬性聯想遊戲、簡圖聯想遊戲、圖繪展開遊戲等四項遊戲內容。用戶可在遊戲歷程的作答中,分析出精緻性創意或創新性思考力表現。

負責的工作內容為:

  • 思考力遊戲程式開發 : 使用 Android Studio 以 Java 語言進行遊戲平台開發
  • 自動化評分機制設計 : 使用機器學習技術 (k-NN) 為文字做答分類,並以 fastText 預訓練的文字向量初始化用戶作答,計算作答與工研院提供的知識概念圖的相似程度進行分數計算
  • 伺服器建設 : 使用 AWS EC3 架設 Apache 伺服器,以建立並傳遞資料庫資料 (使用 HTTP Post & Get methods)
  • 資料庫建設 : 使用 MariaDB 進行資料庫建置,並自動化新增、修改用戶資料

教學助理  國立臺灣師範大學

二月 2019 - 六月 2019

資料庫系統 (碩一)

  • 準備兩堂實習課程,教導如何操作架設 PHP 網頁、架設資料庫
  • 批改作業
  • 協助教授監考

2019年9月-2020年1月

資料結構 (碩二)

  • 協助教授設計功課
  • 批改作業
  • 協助教授監考

程式設計實習生  國立台灣師範大學心理與教育測驗研究發展中心

九月 2017 - 六月 2018

負責的工作內容為:

  • 自動化資料爬取 : 設計 C# 動態連結程式庫 (DLL),透過傳入欲搜尋之書籍名稱或ISBN,對目標網頁的伺服器發出 requests ,回傳書籍資訊
  • 資料庫建設與管理 : 使用 SQL Server 進行資料庫建置

學歷

國立臺灣師範大學

資訊工程學

2018 - 2020


國立高雄科技大學

資訊工程學

2014 - 2018


專案

Master Thesis - Explainable Recommendation System for Solving Review Loss

  • Proposed a review-base recommendation system named HANN-Plus, a hierarchical attention neural network to model user’s preference and product’s preference
  • HANN-Plus not only can provides rating prediction, but also can be used to generate the representation for making user aware of why such products are recommended.
  • Extensive experiments on real-world datasets of Amazon illustrate that HANN-Plus outperforms the state-of-the-art rating prediction methods

Torrance Tests of Creative Thinking (TTCT) 

  • Built an android application for TTCT (Thinking App), a test of creativity, originally involved simple tests of divergent thinking and other problem-solving skills
  • Host MariaDB server to query and update user data daily
  • Implemented machine learning for scoring of TTCT: fastText word embedding to initialize user’s data, k nearest neighbors to calculate the similarity between user’s data and ConceptNet from Academia Sinica

Navigation System with Multiple Feature

  • Proposed a path planning algorithm extended from A-star algorithm with real-time traffic and turning costs
  • Host SQL server to query and update road speed data, crawling from Kaohsiung City  Government every 5 minute
  • User interface design by implementing Open Street Map API and Google Map API

自傳

你好,我是陳佑翔,資訊工程學系出身,對新技術充滿好奇心,並樂於解決問題。

在我的大學生涯中,除了修課精進資訊工程的專業,也曾參與高速公路 ETC 創意競賽、華南 Fintech 金融科技創新競賽以提升自身的競爭能力。大學三年級時,師大心理與教育測驗研究發展中心擔任程式設計工程師,負責開發自動化資料爬取程式庫(DLL),並進行資料庫建設與管理。

碩士期間,我進入資料探勘實驗室,主要的研究領域是深度學習、自然語言、推薦系統,並深度探討協同過濾、矩陣分解、基於附帶資訊的可解釋推薦系統 (結合用戶評論、知識圖譜等資訊進行用戶表徵學習)。我的論文 - 提供具可解釋並改善評論缺漏問題之推薦系統,發表基於評論之階層式注意力神經網路模型 - HANN-Plus。HANN-Plus 透過學習用戶資料及評論文本的表徵,增進模型預測效能,不僅可為用戶進行商品推薦,也能對推薦結果生成文字解釋內容。

綜合以上學經歷,希望能結合所學,從事資料科學家、機器學習工程師相關的工作。感謝您撥空考慮這份履歷,希望能與您會面討論如何為貴公司做出貢獻,請隨時以電子郵件 [email protected] 與我聯繫。


陳 佑翔

Autobiography

Dear HR Recruiter,

My name is Sean, a master graduate from National Taiwan Normal University in July 2020 with Computer Science and Information Engineering. I am always a curious person who think independently and willingness to learn state-of-the-art techniques.

While exploring my passion for Computer Science during college, I participated ETC Freeway Travel Time Prediction Competition, Hua Nan Fintech Innovation Competition and won the best award. Besides, in the senior of university, I am also an intern of Research Center for Psychological and Educational Testing. My job is to crawl the book information from several libraries and manage the database using SQL Server.

During my master's degree, I have developed extensive knowledge and expertise in the field machine learning. Besides collecting and examining large datasets, I am fully skilled in creating and implementing professional data forecasting models. 

For my master's thesis, I researched heavily in Deep Learning, Natural Language Processing, Recommendation System. Furthermore, I focus on the research in Collaborative Filtering, Matrix Factorization and representation learning in Explainable Recommendation System with diverse side information (e.g. review, knowledge graph). 

My thesis "Explainable Recommendation System for Solving Review Loss", proposed a review-based framework named HANN-Plus, a hierarchical attention neural network, which can simultaneously predict precise ratings and generate textual explanation to simulate user experience for making user aware of why such products are recommended.

Thank you for your time and consideration. I am looking forward to meeting to you about the possibility of my joining and how can I contribute to your team. Please feel free to reach me via Email at [email protected] to arrange for an interview. 


Sincerely,

Sean Chen