SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.02300 · ACL · 2021

AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER

Huiqiang Jiang, Qianhui Wu, Börje Karlsson, Yi Guan, Weile Chen

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

Neural methods have been shown to achieve high performance in Named Entity Recognition (NER), but rely on costly high-quality labeled data for training, which is not always available across languages. While previous works have shown that unlabeled data in a target language can be used to improve crosslingual model performance, we propose a novel adversarial approach (AdvPicker) to better leverage such data and further improve results. We design an adversarial learning framework in which an encoder learns entity domain knowledge from labeled source-language data and better shared features are captured via adversarial training -where a discriminator selects less language-dependent target-language data via similarity to the source language. Experimental results on standard benchmark datasets well demonstrate that the proposed method benefits strongly from this data selection process and outperforms existing state-ofthe-art methods; without requiring any additional external resources (e.g., gazetteers or via machine translation). 1

For agents

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

get_harvested_code_for_paper("2106.02300")
get_code_for_paper("2106.02300")
have("2106.02300")

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

curl https://syntology.ai/api/ran/2106.02300.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.02300.svg)](https://syntology.ai/paper/2106.02300)

Connect an agent — have() is free.