PhD student in AI and Machine Learning


portrait

About me

Hi, I am a PhD student in Northwestern University working on AI and Machine Learning. My current research focuses on (1) integrating deep learning with symbolic representations; (2) designing more efficient reinforcement learning algorithms; (3) applications in real-world natural language understanding and program synthesis tasks. For example, my recent works designed a hybrid neural network model (Neural Symbolic Machines) and proposed a novel policy gradient method (Memory Augmented Policy Optimization) for efficient training. It is the first end-to-end model that achieves new state-of-the-art on two challenging semantic parsing / program synthesis benchmarks.


News

August, 2018: thesis defense and graduation.

July, 2018: released our paper Memory Augmented Policy Optimization for Program Synthesis with Generalization on Arxiv, and open sourced the code on Github.

Feb, 2018: finished internship in Google Brain with Quoc Le and Ni Lao.

July, 2017: presented our paper Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision at ACL 2017 in Vancouver, CA.

October, 2017: finished research internship in DeepMind, London.

Jan, 2017: visited Microsoft Research Asia in Beijing and presented my work in neural semantic parsing.

Nov, 2017: visited FAIR, and presented my work in neural semantic parsing.

Timeline



Industrial Experience

Research Intern, Google, Mountain View, November 2017 - February 2018

Research Intern, DeepMind, London, June 2017 - October 2017

Research Intern, Google, Mountain View, June 2016 - September 2016

Research Intern, Google, Mountain View, June 2015 - September 2016


Academic Experience

Research Assistant, Northwestern University, 2013 - Present

TA and lecturing in EECS349 Machine Learning, 2017

TA and lecturing in EECS349 Machine Learning, 2016

TA in EECS325 AI programming, 2014


Education

PhD in Computer Science and Cognitive Science, Northwestern University, Evanston, US, Sept 2013 - Present

BSc in Physics, Peking University, Beijing, China, June 2016 - Sept 2016

Publications


Memory Augmented Policy Optimization for Program Synthesis with Generalization
Liang, C., Norouzi, M., Berant, J., Le, Q., and Ni, L.
Under review for NIPS 2018


Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
Liang, C., Berant, J., Le, Q., Forbus, K., and Ni, L.
Oral Presentation, ACL 2017


Definition Modeling: Learning to define word embeddings in natural language
Noraset, T., Liang, C., Birnbaum, L., and Downey, D.
Poster, AAAI 2017


Representation and Computation in Cognitive Models
Forbus, K., Liang, C., and Rabkina, I.
Journal, Topics in Cognitive Science 2017


Learning Paraphrase Identification with Structural Alignment
Liang, C., Paritosh, P., Rajendran, V., and Forbus, K.
Oral Presentation, IJCAI 2016


Learning Plausible Inferences from Semantic Web Knowledge by Combining Analogical Generalization with Structured Logistic Regression
Liang, C. and Forbus, K.
Oral Presentation, AAAI 2015


Constructing Hierarchical Concepts via Analogical Generalization
Liang, C. and Forbus, K.
Poster, CogSci 2014

Projects


mapo nsm

Memory Augmented Policy Optimization (MAPO)

A new policy optimization formulation that incorporates a memory buffer of promising trajectories to accelerate and stabilize policy gradient training, especially given sparse rewards. It is the first RL approach that achieves new state-of-the-art on learning program synthesis / semantic parsing for database tables from weak supervision.

Paper Github Repository


neural symbolic machine overview

Neural Symbolic Machines (NSM)

An end-to-end neural network learns to write Lisp programs to answer questions over a large open-domain knowledge base. First end-to-end neural network model that achieved new state-of-the-art result on learning semantic parsing over Freebase with weak supervision.

Paper Github Repository


neural symbolic machine overview

Definition Modeling

Distributed representations of words (embeddings) have been shown to capture lexical semantics, based on their effectiveness in word similarity. In this project, we study whether it is possible to utilize the embeddings to generate dictionary definitions of words, as a more direct and transparent representation of the embeddings' semantics.

Paper Github Repository Demo


SlogAn KBC overview

Knowledge Base Completion

Distributed representations of words (embeddings) have been shown to capture lexical semantics, based on their effectiveness in word similarity. In this project, we study whether it is possible to utilize the embeddings to generate dictionary definitions of words, as a more direct and transparent representation of the embeddings' semantics.

Paper


neural symbolic machine overview

Learning Concept Hierarchy

Distributed representations of words (embeddings) have been shown to capture lexical semantics, based on their effectiveness in word similarity. In this project, we study whether it is possible to utilize the embeddings to generate dictionary definitions of words, as a more direct and transparent representation of the embeddings' semantics.

Paper Github Repository

portrait

TensorFlow Char-RNN

A TensorFlow implementation of Andrej Karpathy's Char-RNN, a character level language model using multilayer Recurrent Neural Network (RNN, LSTM or GRU). See his blog article The Unreasonable Effectiveness of Recurrent Neural Network to learn more about this model.

Github Repository Blog article

portrait

TensorFlow Policy Gradient

A simple TensorFlow implementation of policy gradient, tested with Cartpole in Open AI Gym.

Github Repository Blog article