Jie Cai


A Label Informative Wide & Deep Classifier for Patents and Papers
Muyao Niu | Jie Cai
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

In this paper, we provide a simple and effective baseline for classifying both patents and papers to the well-established Cooperative Patent Classification (CPC). We propose a label-informative classifier based on the Wide & Deep structure, where the Wide part encodes string-level similarities between texts and labels, and the Deep part captures semantic-level similarities via non-linear transformations. Our model trains on millions of patents, and transfers to papers by developing distant-supervised training set and domain-specific features. Extensive experiments show that our model achieves comparable performance to the state-of-the-art model used in industry on both patents and papers. The output of this work should facilitate the searching, granting and filing of innovative ideas for patent examiners, attorneys and researchers.


A Multigraph Model for Coreference Resolution
Sebastian Martschat | Jie Cai | Samuel Broscheit | Éva Mújdricza-Maydt | Michael Strube
Joint Conference on EMNLP and CoNLL - Shared Task


Unrestricted Coreference Resolution via Global Hypergraph Partitioning
Jie Cai | Éva Mújdricza-Maydt | Michael Strube
Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task


Evaluation Metrics For End-to-End Coreference Resolution Systems
Jie Cai | Michael Strube
Proceedings of the SIGDIAL 2010 Conference

End-to-End Coreference Resolution via Hypergraph Partitioning
Jie Cai | Michael Strube
Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010)