Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields

Domain:

natural language processing

Record type:

paper
Creator:
CotDuh
Host:avatar
Low-resource named entity recognition is still an open problem in NLP. Most state-of-the-art systems require tens of thousands of annotated sentences in order to obtain high performance. However, for most of the world's languages, it is unfeasible to obtain such annotation. In this paper, we present a transfer learning scheme, whereby we train character-level neural CRFs to predict named entities for both high-resource languages and low resource languages jointly. Learning character representations for multiple related languages allows transfer among the languages, improving F1 by up to 9.8 points over a loglinear CRF baseline. IJCNLP 2017

Visit

arxiv.org

Tasks

information extractionnamed entity recognitiontransfer learning

Tags

Computation and Language

Similar

Named Entity Recognition for Setswana Language: A conditional Random Fields (CRF) ApproachNamed Entity Recognition in Low-resource Languages using Cross-lingual distributional word representationAnalysing Cross-Lingual Transfer in Low-Resourced African Named Entity RecognitionMeta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine LanguagesCross-lingual Transfer Performance in Low-resource Named Entity Recognition via Transliterated Scripts and Expanded VocabulariesPerformance comparison of cross-lingual transfer learning methods for Named Entity Recognition in low-resource African languages

Named Entity Recognition for Setswana Language: A conditional Random Fields (CRF) Approach

Named Entity Recognition in Low-resource Languages using Cross-lingual distributional word representation

Named Entity Recognition (NER) is a fundamental task in many NLP applications that seek to identify

Analysing Cross-Lingual Transfer in Low-Resourced African Named Entity Recognition

Transfer learning has led to large gains in performance for nearly all NLP tasks while making downst

Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages

Named-entity recognition (NER) in low-resource languages is usually tackled by finetuning very large

Cross-lingual Transfer Performance in Low-resource Named Entity Recognition via Transliterated Scripts and Expanded Vocabularies

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Performance comparison of cross-lingual transfer learning methods for Named Entity Recognition in low-resource African languages

Cross-lingual transfer learning enables NLP for low-resource languages by leveraging labeled data fr