Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks

10/11/2021
by   Songlin Yang, et al.
0

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

page 1

page 2

page 3

page 4

research
03/09/2022

Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing

Nested named entity recognition (NER) has been receiving increasing atte...
research
05/09/2020

The Structured Weighted Violations MIRA

We present the Structured Weighted Violation MIRA (SWVM), a new structur...
research
04/17/2022

Nested Named Entity Recognition as Holistic Structure Parsing

As a fundamental natural language processing task and one of core knowle...
research
12/15/2020

Nested Named Entity Recognition with Partially-Observed TreeCRFs

Named entity recognition (NER) is a well-studied task in natural languag...
research
04/25/2020

Towards Discourse Parsing-inspired Semantic Storytelling

Previous work of ours on Semantic Storytelling uses text analytics proce...
research
03/28/2020

A Dataset of Dockerfiles

Dockerfiles are one of the most prevalent kinds of DevOps artifacts used...
research
04/02/2021

Effect of depth order on iterative nested named entity recognition models

This paper studies the effect of the order of depth of mention on nested...

Please sign up or login with your details

Forgot password? Click here to reset