Kazuki Fujikawa

Machine Learning Engineer

Hi, I'm Kazuki Fujikawa, a machine learning engineer at DeNA. My research interests include machine learning and its application in natural language processing.
[profile]

Resume

Biography

2014 - current

Machine Learning Engineer
DeNA Co., Ltd.

  • AI-driven drug discovery
  • Open domain chatbot
  • Image-based fashion item recomendation
2012 - 2014

M.E. In Computer Science
Graduate School of Engineering, Kobe University, Japan

  • Deep Learning for Text Mining
  • Stock price prediction (Text mining approach using web news articles)
  • Text Mining (Finding Negated expressions using a classifier and heuristics)
2008 - 2012

B.E. In Computer Science
Department of Computer Science and System Engineering, Kobe University, Japan

  • Text Mining (Finding Negated expressions using a classifier and heuristics)

Machine Learning Competitions

International Competitions (Kaggle)

Quora Insincere Questions Classification (2019.02)
4th place
[link]

Domestic Competitions (SIGNATE)

Bayer: Medical Text Mining Challenge (2017.07)
1st place
[link]

Publication

JOURNAL PAPERS

Kazuki Fujikawa, Kazuhiro Seki, and Kuniaki Uehara.
NegFinder: A Web Service for Identifying Negation Signals and Their Scopes.
IPSJ Transactions on Bioinformatics.
[pdf]

INTERNATIONAL CONFERENCE PAPERS (REVIEWED)

Akira Yoshihara, Kazuki Fujikawa, Kazuhiro Seki, and Kuniaki Uehara.
Predicting Stock Market Trends by Recurrent Deep Neural Networks.
In Proceedings of PRICAI 2014: Trends in Artificial Intelligence , pp. 759769, 2014.
[link]

Kazuki Fujikawa, Kazuhiro Seki, and Kuniaki Uehara.
A Hybrid Approach to Finding Negated and Uncertain Expressions in Biomedical Documents.
In Proceedings of the 2nd International Workshop on Managing Interoperability and compleXity in Health Systems, pp. 6774, October 2012.
[pdf], [presentation]

DOMESTIC CONFERENCE

Koichi Hamada, Kazuki Fujikawa, Sosuke Kobayashi, Yuta Kikuchi, Yuya Unno and Masaaki Tsuchida.
対話返答生成における個性の追加反映
第232回自然言語処理研究会 (SIG-NL)
[slide]

Kazuki Fujikawa, Kazuhiro Seki, and Kuniaki Uehara.
Financial Trend Prediction and Analysis through Textual Data.
第28回人工知能学会全国大会(JSAI2014)
[pdf]

Kazuki Fujikawa, Kazuhiro Seki, and Kuniaki Uehara.
Generating Unified Representation for MultiDocuments by Deep Neural Network and its Application to Stock Price Prediction.
人工知能学会 金融情報学研究会(SIGFIN), January 2014.
[pdf]

Kazuki Fujikawa, Kazuhiro Seki, and Kuniaki Uehara.
NegFinder: A Web Service for Identifying Negation Signals and Their Scopes.
情報処理学会 第34回BIO研究発表会, June 2012.
[pdf]

Sayaka Kitaguchi, Koji Kumanami, Kazuki Fujikawa, Taiki Miyanishi.
Twitterを利用した震災情報検索支援システム. 東日本大震災ビッグデータワークショップ - Project 311 - .
2012年10月.
[リンク]

THESES

Kazuki Fujikawa, Kazuhiro Seki, and Kuniaki Uehara.
Generating Unified Representation for MultiDocuments by Deep Neural Network and its Application to Stock Price Prediction.
February 2014.

Kazuki Fujikawa, Kazuhiro Seki, and Kuniaki Uehara.
医療文書を対象とした否定・不確実表現の検出とその影響範囲の推定.
February 2012.


Reserch Interest

  • Machine Learning for NLP
  • Machine Learning for ChemoInfomatics

Skills

  • Python
  • Ruby
  • Docker

Contacts

Email:

Linkedin: https://www.linkedin.com/pub/kazuki-fujikawa/50/621/87b