Mu Yang

Research Assistant, CKIP Lab, Academia Sinica

I currently work as a research assistant at the Institute of Information Science, Academia Sinica, advised by Dr. Wei-Yun Ma at the Chinese Knowledge and Information Processing (CKIP) Lab, conducting researches of natural language processing and computational linguistics.

Previously, I received my master degree at Institute of Applied Mathematical Sciences, National Taiwan University, advised by Dr. Weichung Wang, conducting researches of high-performance parallel computing on hybrid CPU-GPU structures.

I have working experience in Thomas J. Watson Research Center, IBM Corporation as an internship, advised by Dr. I-Hsin Chung, conducting researches of high-performance parallel computing on hybrid CPU-GPU structures.

Résumé

Educations

2015-2017 | Nat'l. Taiwan Univ.
Master of Science

Institute of Applied Mathematical Sciences,
National Taiwan University, Taipei, Taiwan

2011-2015 | Nat'l. Taiwan Univ.
Bachelor of Science

Department of Mathematics,
National Taiwan University, Taipei, Taiwan

Employments

2017-Pres. | Academia Sinica
Research Assistant

CKIP Lab, Institute of Information Science,
Academia Sinica, Taipei, Taiwan

2015-2015 | IBM Corp.
Internship

Thomas J. Watson Research Center,
IBM, Yorktown Heights, NY, USA

Publications & Presentations

Headword-Oriented Entity Linking: A New Entity Linking Task with Dataset and Baseline

Mu Yang, Chi-Yen Chen, Yi-Hui Lee, Qian-Hui Zeng, Wei-Yun Ma, Chen-Yang Shih, Wei-Jhih Chen
2020, 12th International Conference on Language Resources and Evaluation (LREC'20)

Conference

HWE: Word Embedding with Heterogeneous Features

Jhih-Sheng Fan, Mu Yang, Peng-Hsuan Li, Wei-Yun Ma
2019, 13th IEEE International Conference on Semantic Computing (IEEE-ICSC'19)

Conference

Particle Swarm Stepwise Algorithm (PaSS) on Multicore Hybrid CPU-GPU Clusters

Mu Yang, Ray-Bing Chen, I-Hsin Chung, Weichung Wang
2016, 16th IEEE International Conference on Computer and Information Technology (IEEE-CIT'16)

Conference

Highly Scalable Parallelism of Integrated Randomized Singular Value Decomposition with Big Data Applications

Mu Yang
2017, Master's Thesis, National Taiwan University

Parallelized Integration of Multiple Random Sketches from Randomized Singular Value Decomposition with Multi-Level Pairwise Integration Method

Mu Yang, Dawei Chang, Weichung Wang, Su-Yuen Huang, Ting-Li Chen
2019, 7th Asian Pacific Congress on Computational Mechanics (APCOM'19)

Conference

Parallel Implementations of Integrated Singular Value Decomposition (iSVD)

Mu Yang, Su-Yun Huang, Ting-Li Chen, Weichung Wang
2017, 9th SIAM Conference on Computational Science and Engineering (SIAM CSE'17)

Conference

Awards & Certificates

Top 2 Short Answer, Top 3 Multiple Choice, Out of 143 Teams.

2018–2019, Formosa Grand Challenge (Chinese TOEFL-like listening comprehension QA). Official Post

Presentation Excellence Award

2016, 7th Taiwan-Japan Joint Workshop for Young Scholars in Applied Mathematics.

Top 1 Academic Excellence Award

Fall 2011, Department of Mathematics, National Taiwan University

Projects

CKIP CoreNLP

2018-2020

A Python Package of CKIP CoreNLP Toolkits with Sentence Segmentation, Word Segmentation, Part-of-Speech Tagging, Named-Entity Recognition, Sentence Parsing, Co-Reference Resolution.

E-HowNet Parsing and Visualization

2018-2019

A Parser for E-HowNet , and the visualization demo.

CosmEL: Cosmetic Entity Linking

2017-2019

A novel entity linking project on cosmetic domain with dataset and baseline.
This project is an industrial-academic project with PIXNET Corporation.

HWE: Heterogeneous Word Embedding

2017-2018

A general and flexible framework of word embeddings to incorporate each type (e.g. word-sense, part-of-speech, topic) of contextual feature for learning feature-specific word embeddings in an explicit fashion.

iSVD: Integrated Singular Value Decomposition Algorithm

2015-2017

A parallel low-rank approximate singular value decomposition solver using integrated randomized algorithm. Implemented for multinode hybrid CPU-GPU systems.

PaSS: Particle Swarm Stepwise Algorithm

2013-2015

A parallel stochastic search algorithm for information criterion variable selection problems. Implemented for multinode hybrid CPU-GPU systems.