CV

A PDF version is also available here.

Education

• B.S. in Computing, The Hong Kong Polytechnic University, 2012
• M.S. in Language Technologies, Carnegie Mellon University, 2014
• Ph.D in Language and Information Technologies, Carnegie Mellon University, 2020 (expected)

Work experience

• 2019 till now: Research Scientist
  • Petuum Inc.
• 2012 - 2019: Research Assistant
  • Carnegie Mellon University
  • Supervisor: Professor Eduard Hovy and Professor Teruko Mitamura
• Summer 2015: Research Intern at Google Research
  • Google Inc.
  • Work on Verb Phrase Ellipsis to infer ellided predicate information in light verbs like “Yes, I do!”
  • Supervisor: Edgar González Pellicer and Daniel Gillick
• Summer 2012: Student Developer at Google Summer of Code
  • DBpedia.org
  • Worked on the DBpedia Spotlight, developed and delivered a collective entity linking system which considers the coherence of all entities in a document context.
  • https://github.com/hunterhector/dbpedia-spotlight

Publications

High Performance Clustering for Web Person Name Disambiguation Using Topic Capturing

PolyUCOMP in TAC 2011 Entity Linking and Slot-Filling

Aggregating skip bigrams into key phrase-based vector space model for web person disambiguation.

Topic Sequence Kernel

Combining Classification with Clustering for Web Person Disambiguation

PolyUCOMP: combining semantic vectors with skip bigrams for semantic textual similarity

Supervised Within-Document Event Coreference using Information Propagation

Detecting Subevent Structure for Event Coreference Resolution

CMU Multiple-choice Question Answering System at NTCIR-11 QA-Lab

Evaluation Algorithms for Event Nugget Detection : A Pilot Study

CMU-LTI at KBP 2015 Event Track

Overview of TAC-KBP 2015 Event Nugget Track

Unsupervised Ranking Model for Entity Coreference Resolution

Exploring the steps of Verb Phrase Ellipsis

Harnessing Deep Neural Networks with Logic Rules

CMU-LTI at KBP 2016 Event Nugget Track

Overview of TAC-KBP 2016 Event Nugget Track

De-duping URLs with Sequence-to-Sequence Neural Networks

JointSem: Combining Query Entity Linking and Entity based Document Ranking

Events Detection, Coreference and Sequencing: What’s next? Overview of the TAC KBP 2017 Event Track.

Graph-Based Decoding for Event Sequencing and Coreference Resolution

Towards Better Text Understanding and Retrieval through Kernel Entity Salience Modeling

Automatic Event Salience Identification

Texar : A Modularized , Versatile , and Extensible Toolbox for Text Generation

Talks

Supervised Within-Document Event Coreference using Information Propagation

May 26, 2014

Talk at LREC 2014, Reykjavik, Iceland

Modularizing Natural Language Processing

February 07, 2020

Tutorial at AAAI 2020, New York, USA

Modularizing Natural Language Processing

April 01, 2020

Tutorial at GTC 2020, New York, USA

Teaching

Script Induction in Probabilistic Way

Coreference Resolution

Computational Semantics for NLP

Neural Networks for NLP