Effective Use of Context in Noisy Entity Linking (D18-1)

Copied to clipboard

Challenge: Effectively using an entity mention's context to disambiguate it is the crux of the entity linking task.
Approach: They propose to use convolutional neural networks to extract cues from context to effectively disambiguate between closely related concepts.
Outcome: The proposed model outperforms previous work on the WikilinksNED test set by 2.8% absolute.

Similar Papers

Contextual Augmentation for Entity Linking using Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Entity Linking involves detecting and linking entity mentions in natural language texts to a knowledge graph.
Approach: They propose a fine-tuned model that integrates entity recognition and disambiguation in a unified framework.
Outcome: The proposed model achieves state-of-the-art on out-of domain datasets and compares with baselines.
Improving Fine-grained Entity Typing with Entity Linking (D19-1)

Copied to clipboard

Challenge: Existing methods for fine-grained entity typing require a large tag set and knowledge of the context.
Approach: They propose a deep neural model that uses context and information from entity linking to improve fine-grained entity typing.
Outcome: The proposed model achieves 5% absolute strict accuracy improvement over the state of the art on two datasets.
Distant Learning for Entity Linking with Automatic Noise Detection (P19-1)

Copied to clipboard

Challenge: Accurate entity linkers have been produced for domains and languages where no or very limited amounts of labeled data are available.
Approach: They propose to use annotated text to learn to link entities without labeling . they frame the task as a multi-instance learning problem and rely on surface matching to create initial noisy labels.
Outcome: The proposed method outperforms the baseline surface matching model for a subset of entities.
Improving Entity Linking by Modeling Latent Relations between Mentions (P18-1)

Copied to clipboard

Challenge: Entity linking systems often exploit relations between textual mentions to decide if the linking decisions are compatible.
Approach: They treat relations as latent variables while optimizing the neural entity-linking model without supervision.
Outcome: The proposed model outperforms its relation-agnostic version and significantly outperformed its relational version.
Fine-Grained Evaluation for Entity Linking (D19-1)

Copied to clipboard

Challenge: Entity Linking (EL) is an Information Extraction task that identifies entity mentions in a text corpus and associates them with an unambiguous identifier in KBs such as Wikipedia, BabelNet, DBpedia, Wikidata and YAGO.
Approach: They propose a fine-grained categorization of different types of entity mentions and links and propose 'fuzzy recall' metric to address the lack of consensus and compare a selection of online EL systems.
Outcome: The proposed task offers a bridge between unstructured text and structured KBs, where EL has applications for semantic search, document classification, relation extraction, and more.
Boosting Entity Linking Performance by Leveraging Unlabeled Documents (P19-1)

Copied to clipboard

Challenge: a new approach to entity linking relies on unlabeled documents and Wikipedia . a supervised approach uses only natural information, such as unlabed documents .
Approach: They propose a method which exploits only naturally occurring information . they construct a high recall list of candidate entities for each mention in an unlabeled document .
Outcome: The proposed model outperforms fully-supervised state-of-the-art systems on standard test sets.
Learning from Context or Names? An Empirical Study on Neural Relation Extraction (2020.emnlp-main)

Copied to clipboard

Challenge: Existing datasets may leak shallow heuristics via entity mentions, thus contributing to the high performance on RE benchmarks.
Approach: They propose an entity-masked contrastive framework for relation extraction to gain a deeper understanding on textual context and type information while avoiding rote memorization of entities.
Outcome: The proposed framework improves the effectiveness and robustness of neural models in different RE scenarios.
Unsupervised Entity Linking with Guided Summarization and Multiple-Choice Selection (2022.emnlp-main)

Copied to clipboard

Challenge: Entity linking is an important task for language understanding.
Approach: They propose a fully unsupervised model that generates a guided summary of the contexts conditioning on a mention and then casts the task to a multiple-choice problem.
Outcome: The proposed model achieves state-of-the-art performance on existing datasets and exiting datasets.
Improving Entity Disambiguation by Reasoning over a Knowledge Base (2022.naacl-main)

Copied to clipboard

Challenge: Recent work in entity disambiguation relies on a limited subset of KB facts to link entities . less common entities are prone to missing or inconsistent KB information, which is problematic for models which rely on 'one source'
Approach: They propose an ED model which links entities by reasoning over a symbolic knowledge base in a fully differentiable fashion.
Outcome: The proposed model outperforms state-of-the-art models on six well-established datasets by 1.3 F1 on average.
The Role of Global and Local Context in Named Entity Recognition (2023.acl-short)

Copied to clipboard

Challenge: Named Entity Recognition (NER) models are usually applied sequentially because of their complexity.
Approach: They explore the impact of global document context on Named Entity Recognition . they find that correctly retrieving global document contextual has a greater impact .
Outcome: The proposed model can retrieve global context better than leveraging local context . authors say the model can push the state of the art further .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations