mlsanityData to 7 Oct 2026

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

arXiv 2109.05716 ↗First posted 13 Sep 2021cs.CLcited by 9

Not on the map. Why?

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

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

20 of 29 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  5. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  6. 2020Autoregressive Entity Retrievalcited by 333
  7. 2020LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentioncited by 326
  8. 2019Zero-Shot Entity Linking by Reading Entity Descriptionscited by 124
  9. 2019Learning Dense Representations for Entity Retrievalcited by 122
  10. 2017Deep Joint Entity Disambiguation with Local Neural Attentioncited by 79
  11. 2018Improving Entity Linking by Modeling Latent Relations between Mentionscited by 53
  12. 2016Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguationcited by 48
8 more
  1. 2021Understanding Hard Negatives in Noise Contrastive Estimationcited by 39
  2. 2019Joint Entity Linking with Deep Reinforcement Learningcited by 27
  3. 2018Collective Entity Disambiguation with Structured Gradient Tree Boostingcited by 16
  4. 2020Zero-shot Entity Linking with Efficient Long Range Sequence Modelingcited by 13
  5. 2019Boosting Entity Linking Performance by Leveraging Unlabeled Documentscited by 12
  6. 2020Learning Cross-Context Entity Representations from Textcited by 12
  7. 2017Learning Distributed Representations of Texts and Entities from Knowledge Basecited by 10
  8. 2021Improving Zero-Shot Entity Retrieval through Effective Dense Representationscited by 6

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 5; 2024: 1.

9 papers.

  1. 2023A Read-and-Select Framework for Zero-shot Entity Linkingcited by 6
  2. 2022Connecting a French Dictionary from the Beginning of the 20th Century to Wikidatacited by 4
  3. 2023Towards Better Entity Linking with Multi-View Enhanced Distillationcited by 3
  4. 2023Proxy-based Zero-Shot Entity Linking by Effective Candidate Retrievalcited by 2
  5. 2023Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decompositioncited by 2
  6. 2024Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrievalcited by 2
  7. 2022Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Promptscited by 1
  8. 2023Revisiting Sparse Retrieval for Few-shot Entity Linkingcited by 1
  9. 2022Named Entity Linking with Entity Representation by Multiple Embeddingscited by 0