Commonsense Reasoning with Knowledge Graphs
Project Description

As one bottleneck for the development of NLP, commonsense reasoning is more and more popular in the NLP community recently. We aim at resolving commonsense reasoning tasks (question answering, dialog generation, semantic role labeling, coreference resolution, etc..) with knowledge graphs (e.g., ASER, ConceptNet, Wordnet, Probase). As this research project is task-oriented, we do not limit the used methods. Both traditional machine learning methods and deep models are encouraged.

Supervisor
SONG Yangqiu
Quota
10
Course type
UROP1100
UROP2100
UROP3100
UROP4100
Applicant's Roles

Help Ph.D. students to prepare baseline models, design algorithms, write papers.

Applicant's Learning Objectives

Know how to analyze and solve commonsense reasoning tasks, more familiar with knowledge graphs, can learn to define a research topic and write research papers.

Complexity of the project
Challenging