Seminar: Distinguishing Semantic Relations with Vector Representations and Neural Networks

Submitted by admin on Tue, 09/18/2018 - 14:00
  • Time: 9:00 - 10:30, Friday, September 21, 2018
  • Place: P.504, T5 Building, Data Science Laboratory, Hanoi University of Science, 334 Nguyen Trai, Thanh Xuan, Hanoi
  • Speaker: Dr. Nguyen Kim Anh, FPT Research and Innovation, FPT Corporation
  • Title: Distinguishing Semantic Relations with Vector Representations and Neural Networks
  • Summary: In the last decade, computational models that distinguish semantic relations are crucial for many applications in Natural Language Processing. These computational models typically distinguish semantic relations by either representing words as vector representations in the vector space, or using neural networks. In this talk, I introduce approaches to improve both vector representations and neural networks in order to address the tasks of distinguishing semantic relations. A series of experiments demonstrate that the proposed models outperform state-of-the-art models and are able to deal well with these tasks.
  • Short biography of speaker: Dr. Kim Anh Nguyen is a research scientist in FTP Technology Innovation, FPT Corporation, where he is working in natural language understanding and deep learning. He was a lecturer at Hung Vuong University, where he worked from 2008 to 2013. He got master degree in computer science at University of Engineering and Technology - Vietnam National University Hanoi in 2013. He has then received a PhD in Computer Science at Institute for Natural Language Processing - University of Stuttgart, Germany in 2018.