SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.07683 · IJCAI · 2020

UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data

Jian-Guang Lou, Zijia Lin, Qianhui Wu, Börje Karlsson, Biqing Huang

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

Prior works in cross-lingual named entity recognition (NER) with no/little labeled data fall into two primary categories: model transfer based and data transfer based methods. In this paper we find that both method types can complement each other, in the sense that, the former can exploit context information via language-independent features but sees no task-specific information in the target language; while the latter generally generates pseudo target-language training data via translation but its exploitation of context information is weakened by inaccurate translations. Moreover, prior works rarely leverage unlabeled data in the target language, which can be effortlessly collected and potentially contains valuable information for improved results. To handle both problems, we propose a novel approach termed UniTrans to Unify both model and data Transfer for cross-lingual NER, and furthermore, to leverage the available information from unlabeled target-language data via enhanced knowledge distillation. We evaluate our proposed UniTrans over 4 target languages on benchmark datasets. Our experimental results show that it substantially outperforms the existing stateof-the-art methods.

For agents

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

get_harvested_code_for_paper("2007.07683")
get_code_for_paper("2007.07683")
have("2007.07683")

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

curl https://syntology.ai/api/ran/2007.07683.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.07683.svg)](https://syntology.ai/paper/2007.07683)

Connect an agent — have() is free.