CLMar 16, 2022

Label Semantics for Few Shot Named Entity Recognition

Amazon
arXiv:2203.08985v1651 citationsh-index: 98
Originality Incremental advance
AI Analysis

This addresses the problem of low-resource named entity recognition for NLP practitioners by providing an incremental improvement through label semantics.

The paper tackles few-shot named entity recognition by incorporating label name semantics into a dual-BERT encoder architecture that matches entity and label representations, achieving improved state-of-the-art results in few-shot benchmarks and competitive performance in standard benchmarks.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes