# Evaluating Design Decisions for Dual Encoder-based Entity Disambiguation

arXiv: https://arxiv.org/abs/2505.11683 · HTML: https://mlsanity.com/paper/2505.11683/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 16 May 2025.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [Learning Dense Representations for Entity Retrieval](https://mlsanity.com/paper/1909.10506/) (2019)
- [Deep Joint Entity Disambiguation with Local Neural Attention](https://mlsanity.com/paper/1704.04920/) (2017)
- [ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking](https://mlsanity.com/paper/2207.04108/) (2022)
- [Improving Entity Linking by Modeling Latent Relations between Mentions](https://mlsanity.com/paper/1804.10637/) (2018)
- [Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking](https://mlsanity.com/paper/2003.05473/) (2020)
- [Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation](https://mlsanity.com/paper/1601.01343/) (2016)
- [Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP](https://mlsanity.com/paper/2106.06830/) (2021)
- [Learning Dynamic Context Augmentation for Global Entity Linking](https://mlsanity.com/paper/1909.02117/) (2019)
- [Empirical Evaluation of Pretraining Strategies for Supervised Entity Linking](https://mlsanity.com/paper/2005.14253/) (2020)
- [Collective Entity Disambiguation with Structured Gradient Tree Boosting](https://mlsanity.com/paper/1802.10229/) (2018)
- [ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget](https://mlsanity.com/paper/2408.00103/) (2024)
- [SpEL: Structured Prediction for Entity Linking](https://mlsanity.com/paper/2310.14684/) (2023)
- [Global Entity Disambiguation with BERT](https://mlsanity.com/paper/1909.00426/) (2019)
- [OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting](https://mlsanity.com/paper/2410.07549/) (2024)
- [A Read-and-Select Framework for Zero-shot Entity Linking](https://mlsanity.com/paper/2310.12450/) (2023)
- [Entity Disambiguation via Fusion Entity Decoding](https://mlsanity.com/paper/2404.01626/) (2024)
- [Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency](https://mlsanity.com/paper/2311.03253/) (2023)
- [Unified Examination of Entity Linking in Absence of Candidate Sets](https://mlsanity.com/paper/2404.11061/) (2024)
- [Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings](https://mlsanity.com/paper/2305.12027/) (2023)
- [REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking](https://mlsanity.com/paper/2404.12788/) (2024)

## Built on by (most cited first, 5 of 5)

- [LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation](https://mlsanity.com/paper/2601.05192/) (2026)
- [Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling](https://mlsanity.com/paper/2605.18007/) (2026)
- [SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information](https://mlsanity.com/paper/2608.10692/) (2026)
- [Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection](https://mlsanity.com/paper/2608.27470/) (2026)
- [From Location Phrases to Geographic Entities: Task-Adapted Retrieval for People Search](https://mlsanity.com/paper/2608.28965/) (2026)

## Abstract (arXiv)

Entity disambiguation (ED) is the task of linking mentions in text to corresponding entries in a knowledge base. Dual Encoders address this by embedding mentions and label candidates in a shared embedding space and applying a similarity metric to predict the correct label. In this work, we focus on evaluating key design decisions for Dual Encoder-based ED, such as its loss function, similarity metric, label verbalization format, and negative sampling strategy. We present the resulting model VerbalizED, a document-level Dual Encoder model that includes contextual label verbalizations and efficient hard negative sampling. Additionally, we explore an iterative prediction variant that aims to improve the disambiguation of challenging data points. Comprehensive experiments on AIDA-Yago validate the effectiveness of our approach, offering insights into impactful design choices that result in a new State-of-the-Art system on the ZELDA benchmark.