Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

natural-language-processing-8

Cross-Lingual Entity Linking

3260 papers • 126 benchmarks • 313 datasets

Cross-lingual entity linking is the task of using data and models available for one language for which ample such resources are available (e.g., English) to solve entity linking tasks (i.e., assigning a unique identity to entities in a text) in another, commonly low-resource, language. Image Source: Towards Zero-resource Cross-lingual Entity Linking

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in cross-lingual-entity-linking-8

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find cross-lingual-entity-linking-8 models and implementations

Datasets

XL-BEL

Subtasks

Variable Disambiguation

Most implemented papers

Joint Multilingual Supervision for Cross-lingual Entity Linking

Shyam Upadhyay, Dan Roth, Nitish Gupta•Fri Aug 31 2018

This work develops the first XEL approach that combines supervision from multiple languages jointly, and trains a single entity linking model for multiple languages, improving upon individually trained models for each language.

40

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Zero-shot Neural Transfer for Cross-lingual Entity Linking

Graham Neubig, Shruti Rijhwani, J. Carbonell, Jiateng Xie•Thu Nov 08 2018

This work proposes pivot-basedentity linking, which leverages information from a highresource “pivot” language to train character-level neural entity linking models that are transferred to the source lowresource language in a zero-shot manner.

48 0

Towards Zero-resource Cross-lingual Entity Linking

Graham Neubig, Shruti Rijhwani, Shuyan Zhou•Sat Sep 28 2019

This work examines the effect of resource assumptions and quantifies how much the availability of these resource affects overall quality of existing XEL systems and proposes three improvements to both entity candidate generation and disambiguation that make better use of the limited resources the authors do have in resource-scarce scenarios.

20 0

Improving Candidate Generation for Low-resource Cross-lingual Entity Linking

Graham Neubig, J. Wieting, Shuyan Zhou, J. Carbonell, Shruti Rijhawani•Tue Dec 31 2019

This paper assesses the problems faced by current entity candidate generation methods for low- resource XEL, then proposes three improvements that reduce the disconnect between entity mentions and KB entries, and improve the robustness of the model to low-resource scenarios.

24 0

Design Challenges in Low-resource Cross-lingual Entity Linking

Dan Roth, Xingyu Fu, Weijia Shi, Zian Zhao, Xiaodong Yu•Sat Oct 31 2020

It is concluded that the LRL setting requires the use of outside-Wikipedia cross-lingual resources and a simple yet effective zero-shot XEL system, QuEL, that utilizes search engines query logs, shows an average increase in gold candidate recall and end-to-end linking accuracy over state-of-the-art baselines.

13 0

Soft Gazetteers for Low-Resource Named Entity Recognition

Graham Neubig, Shruti Rijhwani, Shuyan Zhou, J. Carbonell•Thu Apr 30 2020

This work proposes a method of “soft gazetteers” that incorporates ubiquitously available information from English knowledge bases, such as Wikipedia, into neural named entity recognition models through cross-lingual entity linking.

45 0

Prix-LM: Pretraining for Multilingual Knowledge Base Construction

Ivan Vulic, Nigel Collier, Muhao Chen, Fangyu Liu, Wenxuan Zhou•Fri Oct 15 2021

A unified representation model for multilingual KB construction and completion, Prix-LM, is proposed, which integrates useful multilingual and KB-based factual knowledge into a single model and demonstrates its effectiveness on standard entity-related tasks.

21 0

Cross-lingual citations in English papers: a large-scale analysis of prevalence, usage, and impact

T. Saier, Michael Färber, Tornike Tsereteli•Sat Nov 06 2021

An analysis of cross-lingual citations based on over one million English papers, spanning three scientific disciplines and a time span of three decades, finds an increasing rate of citations to publications written in Chinese, citations being primarily to local non-English languages, and consistency in citation intent between cross- and monolingual citations.

9 0

Efficient Entity Candidate Generation for Low-Resource Languages

Alberto Garc'ia-Dur'an, Akhil Arora, Robert West•Wed Jun 29 2022

An in-depth analysis of the candidate generation problem in the context of cross-lingual entity linking with a focus on low-resource languages and proposes a light-weight and simple solution based on the construction of indexes whose design is motivated by more complex transfer learning based neural approaches.

1 0

Adding a benchmark result helps the community track progress.

Cross-Lingual Entity Linking | State-of-the-Art