SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.00847 · ACL · 2020

Sources of Transfer in Multilingual Named Entity Recognition

Mark Dredze, David Mueller, Nicholas Andrews

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

Named-entities are inherently multilingual, and annotations in any given language may be limited. This motivates us to consider polyglot named-entity recognition (NER), where one model is trained using annotated data drawn from more than one language. However, a straightforward implementation of this simple idea does not always work in practice: naive training of NER models using annotated data drawn from multiple languages consistently underperforms models trained on monolingual data alone, despite having access to more training data. The starting point of this paper is a simple solution to this problem, in which polyglot models are fine-tuned on monolingual data to consistently and significantly outperform their monolingual counterparts. To explain this phenomena, we explore the sources of multilingual transfer in polyglot NER models and examine the weight structure of polyglot models compared to their monolingual counterparts. We find that polyglot models efficiently share many parameters across languages and that fine-tuning may utilize a large number of those parameters.

For agents

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

get_harvested_code_for_paper("2005.00847")
get_code_for_paper("2005.00847")
have("2005.00847")

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

curl https://syntology.ai/api/ran/2005.00847.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.00847.svg)](https://syntology.ai/paper/2005.00847)

Connect an agent — have() is free.