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

TL;DR

AdaK-NER introduces an adaptive top-K method for NER with incomplete annotations, effectively focusing on likely entity paths and significantly improving F-score over previous methods on English and Chinese datasets.

Contribution

The paper proposes AdaK-NER, a novel adaptive top-K approach that enhances NER performance with incomplete annotations by narrowing the search space for entity paths.

Findings

Achieves 2% F-score improvement on CoNLL-2003.

Over 10% F-score improvement on Chinese datasets.

Demonstrates effectiveness across English and Chinese NER tasks.

Abstract

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% in F-score on the CoNLL-2003 and over 10% on two Chinese datasetscompared with the prior state-of-the-art works.