Lune

EMNLP Findings2023

Selecting Key Views for Zero-Shot Entity Linking

Xuhui Sui, Ying Zhang, Kehui Song, Baohang Zhou, Xiaojie Yuan, Wensheng Zhang

Abstract

Entity linking, which aligns mentions in the text to entities in knowledge bases, is essential for many natural language processing tasks. Considering the real-world scenarios, recent research hotspot of entity linking has focused on the zero-shot setting, where mentions need to link to unseen entities and only the description of each entity is provided. This task challenges the language understanding ability of models to capture the coherence evidence between the mention context and entity description. However, entity descriptions often contain rich information from multiple views, and a mention with context only relates to a small part of the information. Other irrelevant information will introduce noise, which interferes with models to make the right judgments. Furthermore, the existence of these information also makes it difficult to synthesize key information. To solve these problems, we select key views from descriptions and propose a KVZEL framework for zero-shot entity linking. Specifically, our KVZEL first adopts unsupervised clustering to form sub views. Then, it employs a mentionaware key views selection module to iteratively accumulate mention-focused views. This puts emphasis on capturing mention-related information and allows long-range key information integration. Finally, we aggregate key views to make the final decision. Experimental results show the effectiveness of our KVZEL and it achieves the new state-of-the-art on the zeroshot entity linking dataset.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking cites A Bidirectional Multi-paragraph Reading Model for Zero-shot Entity Linking
  • A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking cites Zero-shot Entity Linking with Efficient Long Range Sequence Modeling
  • A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking cites Scalable Zero-shot Entity Linking with Dense Entity Retrieval
  • Zero-shot Entity Linking with Efficient Long Range Sequence Modeling cites Scalable Zero-shot Entity Linking with Dense Entity Retrieval
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on6

  1. Scalable Zero-shot Entity Linking with Dense Entity RetrievalLedell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel et al.EMNLP 2020 · 336 citations
  2. Named Entity Recognition for Entity Linking: What Works and What's NextSimone Tedeschi, Simone Conia, Francesco Cecconi, Roberto NavigliEMNLP Findings 2021 · 33 citations
  3. A Bidirectional Multi-paragraph Reading Model for Zero-shot Entity LinkingHongyin Tang, Xingwu Sun, Beihong Jin, Fuzheng ZhangAAAI 2021 · 24 citations
  4. Zero-shot Entity Linking with Efficient Long Range Sequence ModelingZonghai Yao, Liangliang Cao, Huapu PanEMNLP Findings 2020 · 18 citations
  5. A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity LinkingKai Sun, Richong Zhang, Samuel Mensah, Yongyi Mao et al.ACL Findings 2022 · 9 citations

Related papers

  1. A Read-and-Select Framework for Zero-shot Entity LinkingZhenran Xu, Yulin Chen, Baotian Hu, Min ZhangEMNLP Findings 2023 · 1 citation
  2. OpenMEL: Unsupervised Multimodal Entity Linking Using Noise-Free Expanded Queries and Global CoherenceXinyi Zhu, Yongqi Zhang, Lei ChenVLDB 2025 · 2 citations
  3. Learn to Not Link: Exploring NIL Prediction in Entity LinkingFangwei Zhu, Jifan Yu, Hailong Jin, Lei Hou et al.ACL Findings 2023 · 6 citations
  4. Cross-Lingual Transfer in Zero-Shot Cross-Language Entity LinkingElliot Schumacher, James Mayfield, Mark DredzeACL Findings 2021 · 4 citations
  5. OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model PromptingXukai Liu, Ye Liu, Kai Zhang, Kehang Wang et al.EMNLP 2024 · 7 citations
Dusk over the sea between two cliffs drawn in fine vertical lines