Yang Hou

I am a PhD student at Soochow University, advised by Prof. Zhenghua Li. My research focuses on core natural language processing, with particular interests in constituency parsing, dependency parsing, semantic role labeling, Chinese NLP, and large language models for structured prediction and linguistic analysis.

More broadly, I am interested in how linguistic structure can be modeled, induced, and leveraged in neural systems, as well as how large language models can be evaluated and improved for syntax-related tasks.

Publications

2025

1. Dynamic Head Selection for Neural Lexicalized Constituency Parsing

   Yang Hou and Zhenghua Li

   ACL, 2025

   Dynamic head selection for lexicalized parsing.

   @inproceedings{hou2025dhs,
     title = {Dynamic Head Selection for Neural Lexicalized Constituency Parsing},
     author = {Hou, Yang and Li, Zhenghua},
     booktitle = {ACL},
     abbr = {ACL},
     year = {2025},
     selected = {true},
     bibtex_show = {true},
     url = {https://aclanthology.org/},
     code = {https://github.com/ironsword666}
   }

2. Span-based Semantic Role Labeling as Lexicalized Constituency Tree Parsing

   Yang Hou and Zhenghua Li

   ACL Findings, 2025

   We study span-based semantic role labeling from the perspective of lexicalized constituency parsing and present a unified structured formulation.

   @inproceedings{hou2025srl,
     title = {Span-based Semantic Role Labeling as Lexicalized Constituency Tree Parsing},
     author = {Hou, Yang and Li, Zhenghua},
     booktitle = {Findings of ACL},
     abbr = {ACL Findings},
     year = {2025},
     selected = {true},
     bibtex_show = {true},
     url = {https://aclanthology.org/},
     code = {https://github.com/ironsword666}
   }

3. Data Augmentation for Cross-domain Parsing via Lightweight LLM Generation and Tree Hybridization

   Ziyan Zhang, Yang Hou, Chen Gong, and Zhenghua Li

   COLING 2025, 2025

   We propose lightweight LLM-based subtree generation and tree hybridization to improve cross-domain constituency parsing.

   @inproceedings{zhang2025augment,
     title = {Data Augmentation for Cross-domain Parsing via Lightweight LLM Generation and Tree Hybridization},
     author = {Zhang, Ziyan and Hou, Yang and Gong, Chen and Li, Zhenghua},
     booktitle = {Proceedings of the 31st International Conference on Computational Linguistics (COLING)},
     abbr = {COLING 2025},
     year = {2025},
     bibtex_show = {true},
     url = {https://aclanthology.org/2025.coling-main.744/}
   }

2024

1. Character-Level Chinese Dependency Parsing via Modeling Latent Intra-Word Structure

   Yang Hou and Zhenghua Li

   ACL Findings, 2024

   We model latent intra-word structure for character-level Chinese dependency parsing and improve parsing performance.

   @inproceedings{hou2024char,
     title = {Character-Level Chinese Dependency Parsing via Modeling Latent Intra-Word Structure},
     author = {Hou, Yang and Li, Zhenghua},
     booktitle = {Findings of ACL},
     abbr = {ACL Findings},
     year = {2024},
     selected = {true},
     bibtex_show = {true},
     url = {https://aclanthology.org/2024.findings-acl.173/}
   }

2. High-order Joint Constituency and Dependency Parsing

   Yanggan Gu, Yang Hou, Zhefeng Wang, Xinyu Duan, and Zhenghua Li

   COLING 2024, 2024

   We revisit joint constituency and dependency parsing with more efficient decoding and high-order interaction components.

   @inproceedings{gu2024high,
     title = {High-order Joint Constituency and Dependency Parsing},
     author = {Gu, Yanggan and Hou, Yang and Wang, Zhefeng and Duan, Xinyu and Li, Zhenghua},
     booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
     abbr = {COLING 2024},
     year = {2024},
     bibtex_show = {true},
     url = {https://aclanthology.org/2024.lrec-main.713/}
   }

2021

1. A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing

   Yang Hou, Houquan Zhou, Zhenghua Li, Yu Zhang, Min Zhang, Zhefeng Wang, Baoxing Huai, and Nicholas Jing Yuan

   CoNLL, 2021

   We propose a two-stage coarse-to-fine labeling framework for joint word segmentation, POS tagging, and constituent parsing with constrained decoding.

   @inproceedings{hou2021c2f,
     title = {A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing},
     author = {Hou, Yang and Zhou, Houquan and Li, Zhenghua and Zhang, Yu and Zhang, Min and Wang, Zhefeng and Huai, Baoxing and Yuan, Nicholas Jing},
     booktitle = {Proceedings of the 25th Conference on Computational Natural Language Learning (CoNLL)},
     abbr = {CoNLL},
     year = {2021},
     bibtex_show = {true},
     url = {https://aclanthology.org/2021.conll-1.23/}
   }

Talks

• ACL 2025 Oral Presentation
• Lab Seminar Talk

Services

• Reviewer, ARR

Awards

• Outstanding Academic Scholarship