I am a Ph.D. candidate in the Center for Language and Speech Processing at
Johns Hopkins University, working with my advisor Prof. Benjamin Van Durme.
My research interest includes various aspects of natural language processing, focusing on semantics and knowledge discovery on large corpora. My recent work lies at the crossroads between question answering, information extraction and information retrieval.
In addition to natural languages, I'm also interested in programming languages: I design expressive, typesafe DSLs for various domain applications (e.g. deep learning).
Before joining Johns Hopkins, I obtained my B.Sc. in Computer Science from Peking University, working with Prof. Junfeng Hu in the Institute of Computational Linguistics with a focus on word segmentation and network analysis.
My full CV can be found here.
Confidence scoring using whitebox meta-models with linear classifier probes
NIST TAC SM-KBP 2018 system description: JHU/UR pipeline
A test collection for coreferent mention retrieval
A pruned RNNLM lattice-rescoring algorithm for automatic speech recognition
Cadet: Computer Assisted Discovery Extraction and Translation
IJCNLP 2017 Demo
Typesafe abstractions for tensor operations
Discriminative information retrieval for question answering sentence selection
On the relationship between Gaussian stochastic blockmodels and label propagation algorithms
J. Stat. Mech. 2015(3)
Diachronic deviation features in continuous space word representations
CCL 2014 / LNAI 8801
Human-computer interactive Chinese word segmentation: An adaptive Dirichlet process mixture model approach
A Kalman filter based human-computer interactive segmentation system for ancient Chinese texts
CCL 2013 / LNAI 8202
Towards typesafe deep learning in Scala