Hi! I am Pengcheng Yin, a graudate student at the Language Technologies Institute of Carnegie Mellon University.
I am fasincated by one research question: how to develop knowledge represenation models to faciliate querying and reseasoning with natural language? I ground this long-term goal to the following problems:
- Semantic Parsing & Natural Language Programming
- Open Question Answering & Open Knowledge Base
StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing.Pengcheng Yin, Chunting Zhou, Junxian He, Graham Neubig.
Annual Meeting of the Association for Computational Linguistics (ACL), 2018. (To Appear)
Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow.Pengcheng Yin*, Bowen Deng*, Edgar Chen, Bogdan Vasilescu, Graham Neubig.
International Conference on Mining Software Repositories (MSR), 2018. (To Appear)
Learning to Mine Parallel Natural Language/Source Code Corpora from Stack Overflow.Pengcheng Yin*, Bowen Deng*, Edgar Chen, Bogdan Vasilescu, Graham Neubig.
International Conference on Software Engineering (ICSE) Poster Track, 2018. (To Appear)
A Syntactic Neural Model for General-Purpose Code Generation.Pengcheng Yin, Graham Neubig.
Annual Meeting of the Association for Computational Linguistics (ACL), 2017.
Neural Enquirer: Learning to Query Tables in Natural Language.Pengcheng Yin, Zhengdong Lu, Hang Li, Ben Kao.
International Joint Conference on Artificial Intelligence (IJCAI), 2016.
also appear in the 4th International Conference on Learning Representations (ICLR), Workshop Track, 2016.[PDF] | ArXiv Version | ICLR 2016 Workshop Track Poster
Answering Questions with Complex Semantic Constraints on Open Knowledge Bases.Pengcheng Yin, Nan Duan, Ben Kao, Junwei Bao, Ming Zhou.
International Conference on Information and Knowledge Management (CIKM), 2015.[PDF] | [Project Page]
New Word Detection and Tagging on Chinese Twitter Stream.
Miya Liang*, Pengcheng Yin*, S.M. Yiu.
International Conference on Big Data Analytics and Knowledge Discovery (DaWaK), 2015.
Softmax Q-Distribution Estimation for Structured Prediction: A Theoretical Interpretation for RAML.Xuezhe Ma, Pengcheng Yin, Jingzhou Liu, Graham Neubig, Edward Hovy.
DyNet: The Dynamic Neural Network Toolkit.Graham Neubig et al., including Pengcheng Yin.
arXiv preprint arXiv:1701.03980 [link]
- Reviewer: ACL 2017, ACL 2018, Journal of Computer Science and Technology
- External Reviewer: CIKM 2015, ICDM 2015, KDD 2016, KDD 2017
- Research Intern, Internet Services Research Center, Microsoft Research Redmond 2016
- Research Intern, Natural Language Processing Group, Huawei Noah's Ark Lab 2015
- Research Intern, Natural Language Computing Group, Microsoft Research Asia 2014
- Summer Intern, Dept. of Computer Science, The University of Hong Kong 2013