Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks
share
Constituency parsing and nested named entity recognition (NER) are typical nested structured prediction tasks since they both aim to predict a collection of nested and non-crossing spans. There are many previous studies adapting constituency parsing methods to tackle nested NER. In this work, we propose a novel global pointing mechanism for bottom-up parsing with pointer networks to do both tasks, which needs linear steps to parse. Our method obtain the state-of-the-art performance on PTB among all BERT-based models (96.01 F1 score) and competitive performance on CTB7 in constituency parsing; and comparable performance on three benchmark datasets of nested NER: ACE2004, ACE2005, and GENIA. Our code is publicly available at <https://github.com/sustcsonglin/pointer-net-for-nested>
READ FULL TEXT