Entity Linking
277 papers with code • 27 benchmarks • 44 datasets
Assigning a unique identity to entities (such as famous individuals, locations, or companies) mentioned in text (Source: Wikipedia).
Benchmarks
These leaderboards are used to track progress in Entity Linking
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Entity Linking models and implementations
CoNLL
FUNSD
KILT
FIGER
AIDA CoNLL-YAGO
MedMentions
Most implemented papers
Named Entity Recognition with Bidirectional LSTM-CNNs
Named entity recognition is a challenging task that has traditionally required large amounts of knowledge in the form of feature engineering and lexicons to achieve high performance.
Zero-Shot Entity Linking by Reading Entity Descriptions
First, we show that strong reading comprehension models pre-trained on large unlabeled data can be used to generalize to unseen entities.
Scalable Zero-shot Entity Linking with Dense Entity Retrieval
facebookresearch/BLINK
•
•
EMNLP 2020
This paper introduces a conceptually simple, scalable, and highly effective BERT-based entity linking model, along with an extensive evaluation of its accuracy-speed trade-off.
KILT: a Benchmark for Knowledge Intensive Language Tasks
We test both task-specific and general baselines, evaluating downstream performance in addition to the ability of the models to provide provenance.
Efficient One-Pass End-to-End Entity Linking for Questions
facebookresearch/BLINK
•
•
EMNLP 2020
We present ELQ, a fast end-to-end entity linking model for questions, which uses a biencoder to jointly perform mention detection and linking in one pass.
Visual FUDGE: Form Understanding via Dynamic Graph Editing
herobd/FUDGE
•
•
FUDGE edits the graph structure by combining text segments (graph vertices) and pruning edges in an iterative fashion to obtain the final text entities and relationships.
WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types
In this paper, we present WikiDiverse, a high-quality human-annotated MEL dataset with diversified contextual topics and entity types from Wikinews, which uses Wikipedia as the corresponding knowledge base.
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
microsoft/unilm
•
•
In this paper, we propose \textbf{LayoutLMv3} to pre-train multimodal Transformers for Document AI with unified text and image masking.
ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking
amazon-research/ReFinED
•
•
NAACL (ACL) 2022
The model is capable of generalising to large-scale knowledge bases such as Wikidata (which has 15 times more entities than Wikipedia) and of zero-shot entity linking.
Improving Entity Disambiguation by Reasoning over a Knowledge Base
Recent work in entity disambiguation (ED) has typically neglected structured knowledge base (KB) facts, and instead relied on a limited subset of KB information, such as entity descriptions or types.
