# MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations

arXiv: https://arxiv.org/abs/2109.05716 · HTML: https://mlsanity.com/paper/2109.05716/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://mlsanity.com/paper/2010.01057/) (2020)
- [Zero-Shot Entity Linking by Reading Entity Descriptions](https://mlsanity.com/paper/1906.07348/) (2019)
- [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)
- [Improving Entity Linking by Modeling Latent Relations between Mentions](https://mlsanity.com/paper/1804.10637/) (2018)
- [Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation](https://mlsanity.com/paper/1601.01343/) (2016)
- [Understanding Hard Negatives in Noise Contrastive Estimation](https://mlsanity.com/paper/2104.06245/) (2021)
- [Joint Entity Linking with Deep Reinforcement Learning](https://mlsanity.com/paper/1902.00330/) (2019)
- [Collective Entity Disambiguation with Structured Gradient Tree Boosting](https://mlsanity.com/paper/1802.10229/) (2018)
- [Zero-shot Entity Linking with Efficient Long Range Sequence Modeling](https://mlsanity.com/paper/2010.06065/) (2020)
- [Boosting Entity Linking Performance by Leveraging Unlabeled Documents](https://mlsanity.com/paper/1906.01250/) (2019)
- [Learning Cross-Context Entity Representations from Text](https://mlsanity.com/paper/2001.03765/) (2020)
- [Learning Distributed Representations of Texts and Entities from Knowledge Base](https://mlsanity.com/paper/1705.02494/) (2017)
- [Improving Zero-Shot Entity Retrieval through Effective Dense Representations](https://mlsanity.com/paper/2103.04156/) (2021)

## Built on by (most cited first, 9 of 9)

- [A Read-and-Select Framework for Zero-shot Entity Linking](https://mlsanity.com/paper/2310.12450/) (2023)
- [Connecting a French Dictionary from the Beginning of the 20th Century to Wikidata](https://mlsanity.com/paper/2206.11022/) (2022)
- [Towards Better Entity Linking with Multi-View Enhanced Distillation](https://mlsanity.com/paper/2305.17371/) (2023)
- [Proxy-based Zero-Shot Entity Linking by Effective Candidate Retrieval](https://mlsanity.com/paper/2301.13318/) (2023)
- [Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition](https://mlsanity.com/paper/2305.02996/) (2023)
- [Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval](https://mlsanity.com/paper/2405.12801/) (2024)
- [Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts](https://mlsanity.com/paper/2210.14463/) (2022)
- [Revisiting Sparse Retrieval for Few-shot Entity Linking](https://mlsanity.com/paper/2310.12444/) (2023)
- [Named Entity Linking with Entity Representation by Multiple Embeddings](https://mlsanity.com/paper/2205.10498/) (2022)

## Abstract (arXiv)

Entity retrieval, which aims at disambiguating mentions to canonical entities from massive KBs, is essential for many tasks in natural language processing. Recent progress in entity retrieval shows that the dual-encoder structure is a powerful and efficient framework to nominate candidates if entities are only identified by descriptions. However, they ignore the property that meanings of entity mentions diverge in different contexts and are related to various portions of descriptions, which are treated equally in previous works. In this work, we propose Multi-View Entity Representations (MuVER), a novel approach for entity retrieval that constructs multi-view representations for entity descriptions and approximates the optimal view for mentions via a heuristic searching method. Our method achieves the state-of-the-art performance on ZESHEL and improves the quality of candidates on three standard Entity Linking datasets