natural-language-processing-4

Cross-Lingual NER

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in cross-lingual-ner-4

Trend

Dataset

Best Model

Actions

CoNLL Spanish

CoNLL Dutch

CoNLL German

Libraries

i

Use these libraries to find cross-lingual-ner-4 models and implementations

Datasets

Subtasks

No subtasks available.

Most implemented papers

ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models

Sharan Narang, Rami Al-Rfou, Adam Roberts, Colin Raffel, Noah Constant, Linting Xue, Mihir Kale, Aditya Barua•Thu May 27 2021

This paper shows that a standard Transformer architecture can be used with minimal modifications to process byte sequences, characterize the trade-offs in terms of parameter count, training FLOPs, and inference speed, and shows that byte-level models are competitive with their token-level counterparts.

614

Content

CoNLL 2003

MSRA

Europeana French

NER

MasakhaNER2.0

NoDaLiDa Norwegian Bokmål

WikiAnn NER

UNER v1 - PUD (Chinese)

UNER v1 (Danish)

UNER v1 (English)

UNER v1 (Croatian)

UNER v1 (Portuguese)

UNER v1 (Slovak)

UNER v1 (Serbian)

UNER v1 (Swedish)

UNER v1 (Chinese)

UNER v1 (Chinese Simplified)

UNER v1 - PUD (German)

UNER v1 - PUD (English)

UNER v1 - PUD (Portuguese)

UNER v1 - PUD (Russian)

UNER v1 - PUD (Swedish)

UNER v1 (Cebuano)

UNER v1 (Tagalog U)

UNER v1 (Tagalog T)

Europeana Newspapers

WikiNEuRal

UNER v1

0

Paper Graph

Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings

German Rigau, Rodrigo Agerri, Iker García-Ferrero•Sat Oct 22 2022

It is experimentally demonstrated that high capacity multilingual language models applied in a zero-shot (model-based cross-lingual transfer) setting consistently outperform data-basedCross-lingUAL transfer approaches.

25 0

Paper Graph

Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT

Mark Dredze, Shijie Wu•Thu Apr 18 2019

This paper explores the broader cross-lingual potential of mBERT (multilingual) as a zero shot language transfer model on 5 NLP tasks covering a total of 39 languages from various language families: NLI, document classification, NER, POS tagging, and dependency parsing.

723 0

Paper Graph

Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework

Graham Neubig, Yiming Yang, Zirui Wang, Ruochen Xu, J. Carbonell, Jiateng Xie•Wed Oct 09 2019

A simple and novel framework is proposed that combines two previously mutually-exclusive approaches to learning unified multilingual representations using monolingual and cross-lingual objectives jointly, and outperforms existing methods on the MUSE bilingual lexicon induction (BLI) benchmark.

82 0

Paper Graph

Rethinking embedding coupling in pre-trained language models

Melvin Johnson, Sebastian Ruder, Hyung Won Chung, Thibault Févry, Henry Tsai•Fri Oct 23 2020

The analysis shows that larger output embeddings prevent the model's last layers from overspecializing to the pre-training task and encourage Transformer representations to be more general and more transferable to other tasks and languages.

170 0

Paper Graph

T-Projection: High Quality Annotation Projection for Sequence Labeling Tasks

German Rigau, Rodrigo Agerri, Iker García-Ferrero•Mon Dec 19 2022

T-Projection is presented, a novel approach for annotation projection that leverages large pretrained text-to-text language models and state-of-the-art machine translation technology and can help to automatically alleviate the lack of high-quality training data for sequence labeling tasks.

16 0

Paper Graph

Multi-Source Cross-Lingual Model Transfer: Learning What to Share

Claire Cardie, Wei Wang, Ahmed Hassan Awadallah, Xilun Chen, Hany Hassan•Sun Oct 07 2018

This model leverages adversarial networks to learn language-invariant features, and mixture-of-experts models to dynamically exploit the similarity between the target language and each individual source language to further boost target language performance.

119 0

Paper Graph

Entity Projection via Machine Translation for Cross-Lingual NER

Zachary Chase Lipton, Bhargavi Paranjape, Alankar Jain•Fri Aug 30 2019

This work proposes a system that improves over prior entity-projection methods by leveraging machine translation systems twice: first for translating sentences and subsequently for translating entities; and matching entities based on orthographic and phonetic similarity; and identifying matches based on distributional statistics derived from the dataset.

74 0

Paper Graph

Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources

Qianhui Wu, Guoxin Wang, Börje F. Karlsson, Zijia Lin, Hui Chen, Biqing Huang, Chin-Yew Lin•Wed Nov 13 2019

This paper presents a meta-learning algorithm to find a good model parameter initialization that could fast adapt to the given test case and proposes to construct multiple pseudo-NER tasks for meta-training by computing sentence similarities.

72 0

Paper Graph

Zero-Resource Cross-Lingual Named Entity Recognition

Shafiq R. Joty, M Saiful Bari, Prathyusha Jwalapuram•Thu Nov 21 2019

This paper proposes an unsupervised cross-lingual NER model that can transfer NER knowledge from one language to another in a completely unsuper supervised way without relying on any bilingual dictionary or parallel data.

55 0

Paper Graph

Adding a benchmark result helps the community track progress.