Label Semantics for Few Shot Named Entity Recognition

We study the problem of few shot learning for named entity recognition. Specifically, we leverage the semantic information in the names of the labels as a way of giving the model additional signal and enriched priors. We propose a neural architecture that consists of two BERT encoders, one to encode...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-03
Main Authors: Ma, Jie, Ballesteros, Miguel, Doss, Srikanth, Anubhai, Rishita, Mallya, Sunil, Al-Onaizan, Yaser, Roth, Dan
Format: Article
Language:English
Subjects:
Benchmarks
Coders
Computation
Labels
Recognition
Representations
Semantics
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We study the problem of few shot learning for named entity recognition. Specifically, we leverage the semantic information in the names of the labels as a way of giving the model additional signal and enriched priors. We propose a neural architecture that consists of two BERT encoders, one to encode the document and its tokens and another one to encode each of the labels in natural language format. Our model learns to match the representations of named entities computed by the first encoder with label representations computed by the second encoder. The label semantics signal is shown to support improved state-of-the-art results in multiple few shot NER benchmarks and on-par performance in standard benchmarks. Our model is especially effective in low resource settings.
ISSN:2331-8422