Home

About Me

I am a Computational Linguist.

I am currently working at the Language Computing and Web Mining Group, Institute of Computer Science and Technology, Peking University. Before this, I was a Ph.D. candidate at Department of Computational Linguistics & Phonetics of Saarland University, under the supervision of Prof. Dr. Hans Uszkoreit.

Education

Doctor of Engineering Saarland University (Oct. 2009 - April 2012)

Master of Science in Computer Science, Peking University (Sep.2006 - July 2009)

Bachelor of Arts in Applied Linguistics, Bachelor of Science in Computer Science, Peking University (Sep.2002 - July 2006)

Curriculum Vitae

Research

I study Computational Linguistics.

Mandarin Chinese syntax

I am developing computational resources, including grammars and annotated corpus, for deep linguistic processing for Mandarin Chinese. To learn more, see our OMG project.

Graph-structured semantic parsing

I'm interested in various graphs that can encode deep syntacto-semantic information. Good examples include Minimal Recursion Semantics, Semantic Dependency Graphs, Abstract Meaning Representations. The goal of my research is to develop state-of-the-art parsing techniques to produce high-quality graph-structured semantic analysis. Try our GraSS Parsing Kit.

Publications
  • Team Member 1

    Recent Paper

    Underline

    Parsing to 1-Endpoint-Crossing, Pagenumber-2 Graphs

    Semantic Dependency Parsing via Book Embedding

    ACL 2017

    Deep Dependency Parsing

  • Team Member 1

    Recent Paper

    Underline

    The Covert Helps Parse the Overt

    Parsing for Grammatical Relations via Graph Merging

    CoNLL 2017

    Deep Dependency Parsing

  • Team Member 2

    Recent System

    Underline

    Peking: Building Semantic Dependency Graphs with a Hybrid Parser

    Yantao Du, Fan Zhang, Xun Zhang, Weiwei Sun, Xiaojun Wan

    SemEval 2015, Task 18

    Semantic Dependency Parsing

  • Recent Paper

    Underline

    Transition-based Parsing for Deep Dependency Structures

    Towards Accurate and Efficient Chinese Part-of-Speech Tagging

    Computational Linguistics 2016

    Deep Dependency Parsing, Mandarin

  • Recent Talk

    Underline

    Parsing for Graph-Structured Semantic Representations

    slide

    PKU Interest Group on Language, Logic, Cognition and Computation

    May 28, 2015

    Semantic Dependency Parsing

NLP Resources

Plan 1

OMG

I'm writting an HPSG grammar under the DELPH-IN framework.


Plan 2

GraSS

GraSS parsing kit is developed under our ongoing investigation of graph-structured representations.


Plan 3

PKU lexer

PKU lexer is a state-of-the-art system for Chinese lexical processing.


Resources

Download them!

Use them!

Teaching

Introduction to Formal Syntax

In this course, we discuss several syntactic theories. The focus is among others on the following topics: Transformational Generative Grammar, Lexical Functional Grammar, Head-Driven Phrase Structure Grammar, Tree-Adjoining Grammar and Combinatory Categorial Grammar.
Zur Homepage des Kurses

Empirical Methods in Natural Language Processing

This course is an introduction to data-driven methods applied to natural language processing. The emphasis is on various structured prediction models and their application to tagging, POS tagging, syntactic parsing, semantic parsing, etc.

  • Introduction to

    Formal Syntax

    Product 1

    FS

    About Syntactic Theories

  • Empirical Methods in

    Natural Language Processing

    Product 3

    EMNLP

    About Statistical NLP