Songlin Yang

yangsl (at) shanghaitech (dot) edu (dot) cn

About Me

My name is Songlin Yang (杨松霖). Currently, I am a third-year graduate student at ShanghaiTech University (expected to graduate in 2023) and advised by Prof. Kewei Tu. Before this, I received my Bachelor's degree from Southern University of Science and Technology (SUSTech).

I will be joining the department of EECS at MIT as a PhD student in the fall of 2023.

Publication

[Google Scholar] [Semantic Scholar] (* denotes equal contributions)

• Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars

  Songlin Yang, Roger P. Levy, Yoon Kim.

  In Proceedings of ACL, 2023. [code]

• Don’t Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span Selection

  Songlin Yang, Kewei Tu.

  In Proceedings of ACL, 2023. [code]

• Structured Mean-Field Variational Inference for Higher-Order Span-Based Semantic Role Labeling

  Wei Liu, Songlin Yang, Kewei Tu.

  In Findings of ACL, 2023. [code]

• Semantic Dependency Parsing with Edge GNNs

  Songlin Yang, Kewei Tu.

  In Findings of EMNLP, 2022.

• Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs

  Songlin Yang*, Wei Liu*, Kewei Tu.

  In Proceedings of NAACL, 2022. [code] [slides]

• Headed-Span-Based Projective Dependency Parsing

  Songlin Yang, Kewei Tu.

  In Proceedings of ACL, 2022. [code] [slides]

• Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing

  Chao Lou, Songlin Yang, Kewei Tu.

  In Proceedings of ACL, 2022. [code] [slides]

• Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks

  Songlin Yang, Kewei Tu.

  In Proceedings of ACL, 2022. [code] [slides]

• Combining (Second-Order) Graph-based and Headed-Span-Based Projective Dependency Parsing

  Songlin Yang, Kewei Tu.

  In Findings of ACL, 2022. [code]

• Neural Bi-Lexicalized PCFG Induction

  Songlin Yang, Yanpeng Zhao, Kewei Tu.

  In Proceedings of ACL, 2021. [code] [slides]

• PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols

  Songlin Yang, Yanpeng Zhao, Kewei Tu.

  In Proceedings of NAACL, 2021, [code] [slides]

• Second-Order Unsupervised Neural Dependency Parsing

  Songlin Yang, Yong Jiang, Wenjuan Han, Kewei Tu.

  In Proceedings of COLING, 2020, [code]

Education

• 2020-2023, ShanghaiTech, M.S. in computer science
• 2016-2020, SUSTech, B.E. in computer science