Zhibin Chen

Zhibin Chen

Postgraduate of AAIS and WICT of Peking Univ., interested in NLP and Graph Learning.

Publications

Entailment Graph Learning with Textual Entailment and Soft Transitivity

Published in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022

This paper propose a two-stage Entailment Graph construction method, called Entailment Graph with Textual Entailment and Transitivity (EGT2), which learns the local entailment relations by recognizing the textual entailment between template sentences formed by typed CCG-parsed predicates and then uses three novel soft transitivity constraints to consider the logical transitivity in entailment structures.

Recommended citation: Zhibin Chen, Yansong Feng, and Dongyan Zhao. 2022. Entailment Graph Learning with Textual Entailment and Soft Transitivity. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5899–5910, Dublin, Ireland. Association for Computational Linguistics. https://aclanthology.org/2022.acl-long.406.pdf

Integrating Manifold Knowledge for Global Entity Linking with Heterogeneous Graphs

Published in Data Intelligence (2022), 2022

This paper presents a novel HEterogeneous Graph-based Entity Linker (HEGEL) for global entity linking, which builds an informative heterogeneous graph for every document to collect various linking clues, and utilizes a novel heterogeneous graph neural network (HGNN) to integrate the different types of manifold information and model the interactions among them.

Recommended citation: Chen, Z., Wu, Y., Feng, Y., & Zhao, D. (2022). Integrating Manifold Knowledge for Global Entity Linking with Heterogeneous Graphs. Data Intelligence, 4(1), 20-40. https://direct.mit.edu/dint/article-pdf/4/1/20/1985039/dint_a_00116.pdf