SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.07216 · 2021

Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We study learning named entity recognizers in the presence of missing entity annotations. We approach this setting as tagging with latent variables and propose a novel loss, the Expected Entity Ratio, to learn models in the presence of systematically missing tags. We show that our approach is both theoretically sound and empirically useful. Experimentally, we find that it meets or exceeds performance of strong and state-of-the-art baselines across a variety of languages, annotation scenarios, and amounts of labeled data. In particular, we find that it significantly outperforms the previous state-of-the-art methods from Mayhew et al. (2019) and Li et al. (2021) by +12.7 and +2.3 F1 score in a challenging setting with only 1,000 biased annotations, averaged across 7 datasets. We also show that, when combined with our approach, a novel sparse annotation scheme outperforms exhaustive annotation for modest annotation budgets.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2108.07216")
get_code_for_paper("2108.07216")
have("2108.07216")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2108.07216.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2108.07216.svg)](https://syntology.ai/paper/2108.07216)

Connect an agent — have() is free.