Evaluating Design Decisions for Dual Encoder-based Entity Disambiguation

Challenge:	Entity disambiguation (ED) is the task of linking mentions in text to corresponding entries in a knowledge base.
Approach:	They propose a document-level Dual Encoder model that embeds mentions and label candidates in a shared embedding space and applies a similarity metric to predict the correct label.
Outcome:	The proposed model improves the disambiguation of ambiguous mentions of entities in text to their respective KB entries.

Similar Papers

Overview

Challenge

Approach

Outcome

ZELDA: A Comprehensive Benchmark for Supervised Entity Disambiguation (2023.eacl-main)

Copied to clipboard

Marcel Milich, Alan Akbik

Challenge:	Entity disambiguation (ED) is the task of disambiguating named entity mentions in text to unique entries in a knowledge base.
Approach:	They propose a benchmark for entity disambiguation that includes a unified training data set, entity vocabulary, candidate lists and challenging evaluation splits covering 8 different domains.
Outcome:	The proposed benchmark is based on a unified training data set, entity vocabulary, candidate lists and evaluation splits covering 8 different domains.

Entity Embedding Completion for Wide-Coverage Entity Disambiguation (2022.findings-emnlp)

Copied to clipboard

Daisuke Oba, Ikuya Yamada, Naoki Yoshinaga, Masashi Toyoda

Representation Learning

Challenge:	Existing state-of-the-art ED models do not address out-of vocabulary entities that are absent from training data.
Approach:	They propose to extend a state-of-the-art ED model by dynamically computing embeddings of out-ofvocabulary entities by using entity descriptions and mention contexts.
Outcome:	The proposed model performs comparable to existing models whose embeddings are trained for all candidate entities as well as embedd-free models.

Entity Disambiguation via Fusion Entity Decoding (2024.naacl-long)

Copied to clipboard

Junxiong Wang, Ali Mousavi, Omar Attia, Ronak Pradeep, Saloni Potdar, Alexander Rush, Umar Farooq Minhas, Yunyao Li

Semantic Text Processing

Challenge:	Existing generative approaches demonstrate improved accuracy compared to classification approaches under the standardized ZELDA benchmark.
Approach:	They propose an encoder-decoder model to disambiguate entities with more detailed entity descriptions.
Outcome:	The proposed model outperforms existing classification models on the ZELDA benchmark and on retrieval/reader frameworks.

Improving Entity Disambiguation by Reasoning over a Knowledge Base (2022.naacl-main)

Copied to clipboard

Tom Ayoola, Joseph Fisher, Andrea Pierleoni

Knowledge Representation

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.

Contextualized End-to-End Neural Entity Linking (2020.aacl-main)

Copied to clipboard

Haotian Chen, Xi Li, Andrej Zukov Gregoric, Sahil Wadhwa

Semantic Text Processing

Challenge:	a proposed entity linking model that disjointly applies MD and ED from the same contextualized BERT embeddings is able to generalize better.
Approach:	They propose an entity linking (EL) model that jointly learns mention detection (MD) and entity disambiguation (ED) they propose to use task-specific heads on top of shared BERT contextualized embeddings to learn MD and ED.
Outcome:	The proposed model achieves state-of-the-art results across a standard EL dataset and under a setting where hand-crafted candidate sets are not available.

ExtEnD: Extractive Entity Disambiguation (2022.acl-long)

Copied to clipboard

Edoardo Barba, Luigi Procopio, Roberto Navigli

Information Extraction & Text Mining

Challenge:	Entity disambiguation (ED) is a task in natural language processing that requires a large pre-trained language model to perform.
Approach:	They propose a local formulation for Entity Disambiguation (ED) that frames this task as a text extraction problem and propose two Transformer-based architectures that implement it.
Outcome:	The proposed model outperforms all its competitors in terms of data efficiency and raw performance on 4 out of 4 benchmarks.

Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency (2023.findings-emnlp)

Copied to clipboard

Zilin Xiao, Linjun Shou, Xingyao Zhang, Jie Wu, Ming Gong, Daxin Jiang

Semantic Text Processing

Challenge:	Existing entity disambiguation methods struggle to capture explicit discourse-level dependencies, resulting in incoherent predictions at the abstract level.
Approach:	They propose an unsupervised variational autoencoder to extract latent topic vectors of context sentences to enhance coherence of entity predictions.
Outcome:	The proposed system achieves state-of-the-art on popular ED benchmarks with an average improvement of 1.3 F1 points.

Improving Neural Entity Disambiguation with Graph Embeddings (P19-2)

Copied to clipboard

Özge Sevgili, Alexander Panchenko, Chris Biemann

Semantic Text Processing

Challenge:	Entity Disambiguation (ED) is the task of linking an ambiguous entity mention to a corresponding entry in a knowledge base.
Approach:	They propose a method that integrates structured information from the knowledge base with unstructured information from text-based representations.
Outcome:	The proposed method improves on a graph of hyperlinks between Wikipedia articles and a state-of-the-art neural ED model.

Global Entity Disambiguation with BERT (2022.naacl-main)

Copied to clipboard

Ikuya Yamada, Koki Washio, Hiroyuki Shindo, Yuji Matsumoto

Semantic Text Processing

Challenge:	Entity disambiguation (ED) is a task of assigning mentions to referent entities in a knowledge base.
Approach:	They propose a global entity disambiguation (ED) model based on BERT . they train the model using a large entity-annotated corpus obtained from Wikipedia .
Outcome:	The proposed model can disambiguate masked entities based on words and non-masked ones at the inference time.

Robustness Evaluation of Entity Disambiguation Using Prior Probes: the Case of Entity Overshadowing (2021.emnlp-main)

Copied to clipboard

Vera Provatorova, Samarth Bhargav, Svitlana Vakulenko, Evangelos Kanoulas

Robustness in NLP

Challenge:	Entity disambiguation (ED) is the last step of entity linking when candidate entities are reranked according to the context they appear in.
Approach:	They propose a dataset that includes 16K short text snippets annotated with entity mentions to evaluate EL models.
Outcome:	The proposed dataset shows that the performance of EL systems is overestimated . the results show that the EL system performance is significantly better on the ShadowLink benchmark .