Sotabase

Career

· Research Intern, Microsoft Research2013–2013
· Research Assistant, Columbia University2009–
· Doctor of Philosophy in Computer Science, Columbia University2008–2014
· MS in Computer Science, Columbia University2006–2008
· Research Assistant, Institute of Linguistics, Academia Sinica2006–2006
· Research Assistant, Institute of Information Science, Academia Sinica2000–2004
· Master of Science in Computer Science and Information Engineering, National Chiao Tung University1997–1999
· Research Intern, Industrial Technology Research Institute1995–1996
· Bachelor of Engineering in Computer Science and Engineering, Yuan Ze University1993–1997

Publications (60)

GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction
Annual Meeting of the Association for Computational Linguistics · 2019
373
cited
Introduction to CKIP Chinese Word Segmentation System for the First International Chinese Word Segmentation Bakeoff
Workshop on Chinese Language Processing · 2003
183
cited
Unknown Word Extraction for Chinese Documents
International Conference on Computational Linguistics · 2002
125
cited
A Bottom-up Merging Algorithm for Chinese Unknown Word Extraction
Workshop on Chinese Language Processing · 2003
76
cited
Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER
AAAI Conference on Artificial Intelligence · 2019
72
cited
Leveraging Linguistic Structures for Named Entity Recognition with Bidirectional Recursive Neural Networks
Conference on Empirical Methods in Natural Language Processing · 2017
64
cited
Who, What, When, Where, Why? Comparing Multiple Approaches to the Cross-Lingual 5W Task
Annual Meeting of the Association for Computational Linguistics · 2009
37
cited
iComposer: An Automatic Songwriting System for Chinese Popular Music
North American Chapter of the Association for Computational Linguistics · 2019
34
cited
Design of CKIP Chinese Word Segmentation System
Journal of Chinese Language and Computing · 2004
33
cited
Uniform and Effective Tagging of a Heterogeneous Giga-word Corpus
International Conference on Language Resources and Evaluation · 2006
31
cited
A Deep Learning Framework for Coreference Resolution Based on Convolutional Neural Network
International Computer Science Conference · 2017
25
cited
Relation Extraction Exploiting Full Dependency Forests
AAAI Conference on Artificial Intelligence · 2020
24
cited
Speed Reading: Learning to Read ForBackward via Shuttle
Conference on Empirical Methods in Natural Language Processing · 2018
17
cited
Where’s the Verb? Correcting Machine Translation During Question Answering
Annual Meeting of the Association for Computational Linguistics · 2009
14
cited
Designing a Tag-Based Statistical Math Word Problem Solver with Reasoning and Explanation
ROCLING/IJCLCLP · 2015
12
cited
Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results
arXiv.org · 2023
12
cited
System Combination for Machine Translation through Paraphrasing
Conference on Empirical Methods in Natural Language Processing · 2015
12
cited
H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction
Findings · 2020
11
cited
Word Embedding Evaluation Datasets and Wikipedia Title Embedding for Chinese
International Conference on Language Resources and Evaluation · 2018
9
cited
Detecting and Correcting Syntactic Errors in Machine Translation Using Feature-Based Lexicalized Tree Adjoining Grammars
ROCLING/IJCLCLP · 2012
7
cited
Sotabase
Wei-Yun Ma | Researcher Profile | Sotabase | Sotabase