Rethinking Boundaries: End-To-End Recognition of Discontinuous Mentions with Pointer Networks


  • Hao Fei Wuhan University
  • Donghong Ji Wuhan University
  • Bobo Li Wuhan University
  • Yijiang Liu Wuhan University
  • Yafeng Ren Guangdong University of Foreigh Studies
  • Fei Li Wuhan University


Information Extraction


A majority of research interests in irregular (e.g., nested or discontinuous) named entity recognition (NER) have been paid on nested entities, while discontinuous entities received limited attention. Existing work for discontinuous NER, however, either suffers from decoding ambiguity or predicting using token-level local features. In this work, we present an innovative model for discontinuous NER based on pointer networks, where the pointer simultaneously decides whether a token at each decoding frame constitutes an entity mention and where the next constituent token is. Our model has three major merits compared with previous work: (1) The pointer mechanism is memory-augmented, which enhances the mention boundary detection and interactions between the current decision and prior recognized mentions. (2) The encoder-decoder architecture can linearize the complexity of structure prediction, and thus reduce search costs. (3) The model makes every decision using global information, i.e., by consulting all the input, encoder and previous decoder output in a global view. Experimental results on the CADEC and ShARe13 datasets show that our model outperforms flat and hypergraph models as well as a state-of-the-art transition-based model for discontinuous NER. Further in-depth analysis demonstrates that our model performs well in recognizing various entities including flat, overlapping and discontinuous ones. More crucially, our model is effective on boundary detection, which is the kernel source to NER.




How to Cite

Fei, H., Ji, D., Li, B., Liu, Y., Ren, Y., & Li, F. (2021). Rethinking Boundaries: End-To-End Recognition of Discontinuous Mentions with Pointer Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 12785-12793. Retrieved from



AAAI Technical Track on Speech and Natural Language Processing I