AdaK-NER: An Adaptive Top-K Approach for Named Entity Recognition with Incomplete Annotations

09/11/2021
by   Hongtao Ruan, et al.
0

State-of-the-art Named Entity Recognition(NER) models rely heavily on large amountsof fully annotated training data. However, ac-cessible data are often incompletely annotatedsince the annotators usually lack comprehen-sive knowledge in the target domain. Normallythe unannotated tokens are regarded as non-entities by default, while we underline thatthese tokens could either be non-entities orpart of any entity. Here, we study NER mod-eling with incomplete annotated data whereonly a fraction of the named entities are la-beled, and the unlabeled tokens are equiva-lently multi-labeled by every possible label.Taking multi-labeled tokens into account, thenumerous possible paths can distract the train-ing model from the gold path (ground truthlabel sequence), and thus hinders the learn-ing ability. In this paper, we propose AdaK-NER, named the adaptive top-Kapproach, tohelp the model focus on a smaller feasible re-gion where the gold path is more likely to belocated. We demonstrate the superiority ofour approach through extensive experimentson both English and Chinese datasets, aver-agely improving 2 two Chinese datasetscompared with the prior state-of-the-art works.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/20/2019

Named Entity Recognition with Partially Annotated Training Data

Supervised machine learning assumes the availability of fully-labeled da...
research
11/06/2021

Focusing on Possible Named Entities in Active Named Entity Label Acquisition

Named entity recognition (NER) aims to identify mentions of named entiti...
research
07/30/2020

Neural Modeling for Named Entities and Morphology (NEMO^2)

Named Entity Recognition (NER) is a fundamental NLP task, commonly formu...
research
12/10/2020

Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition

In many scenarios, named entity recognition (NER) models severely suffer...
research
09/30/2018

Neural Entity Reasoner for Global Consistency in NER

We propose Neural Entity Reasoner (NE-Reasoner), a framework to introduc...
research
12/30/2021

KIND: an Italian Multi-Domain Dataset for Named Entity Recognition

In this paper we present KIND, an Italian dataset for Named-Entity Recog...
research
01/16/2018

Adversarial Learning for Chinese NER from Crowd Annotations

To quickly obtain new labeled data, we can choose crowdsourcing as an al...

Please sign up or login with your details

Forgot password? Click here to reset