Lune

EMNLP Findings2022

A Hierarchical N-Gram Framework for Zero-Shot Link Prediction

Mingchen Li, Junfan Chen, Samuel Mensah, Nikolaos Aletras, Xiulong Yang, Yang Ye

Abstract

Knowledge graphs typically contain a large number of entities but often cover only a fraction of all relations between them (i.e., incompleteness). Zero-shot link prediction (ZSLP) is a popular way to tackle the problem by automatically identifying unobserved relations between entities. Most recent approaches use textual features of relations (e.g., surface names or textual descriptions) as auxiliary information to improve the encoded representation. These methods lack robustness as they are bound to support only tokens from a fixed vocabulary and are unable to model out-of-vocabulary (OOV) words. Subword units such as character n-grams have the capability of generating more expressive representations for OOV words. Hence, in this paper, we propose a Hierarchical N-gram framework for Zero-Shot Link Prediction (HNZSLP) that leverages character n-gram information for ZSLP. Our approach works by first constructing a hierarchical n-gram graph from the surface name of relations. Subsequently, a new Transformer-based network models the hierarchical n-gram graph to learn a relation embedding for ZSLP. Experimental results show that our proposed HNZSLP method achieves state-of-the-art performance on two standard ZSLP datasets. 1

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.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Understand the Dynamic World: An End-to-End Knowledge Informed Framework for Open Domain Entity State TrackingMingchen Li, Lifu HuangSIGIR 2023 · 6 citations

Builds on8

  1. Structure-Augmented Text Representation Learning for Efficient Knowledge Graph CompletionBo Wang, Tao Shen, Guodong Long, Tianyi Zhou et al.WWW 2021 · 322 citations
  2. Graph Transformer for Graph-to-Sequence LearningDeng Cai, Wai LamAAAI 2020 · 247 citations
  3. Charformer: Fast Character Transformers via Gradient-based Subword TokenizationYi Tay, Vinh Q. Tran, Sebastian Ruder, Jai Prakash Gupta et al.ICLR 2022 · 198 citations
  4. GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event ExtractionWasi Uddin Ahmad, Nanyun Peng, Kai-Wei ChangAAAI 2021 · 113 citations
  5. OntoZSL: Ontology-enhanced Zero-shot LearningYuxia Geng, Jiaoyan Chen, Zhuo Chen, Jeff Z. Pan et al.WWW 2021 · 96 citations

Related papers

  1. Generative Adversarial Zero-Shot Relational Learning for Knowledge GraphsPengda Qin, Xin Wang, Wenhu Chen, Chunyun Zhang et al.AAAI 2020 · 93 citations
  2. Structure-Aware Zero-Shot Relational Learning for Knowledge Graphs without External KnowledgeKuan Xu, Baoxin Zhang, Shuyue Fan, Ming Chen et al.ACL Findings 2026
  3. Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language ModelsAlessandro De Bellis, Salvatore Bufi, Giovanni Servedio, Vito Walter Anelli et al.EMNLP 2025
  4. Graph-based Relation Mining for Context-free Out-of-vocabulary Word Embedding LearningZiran Liang, Yuyin Lu, Hegang Chen, Yanghui RaoACL 2023 · 5 citations
  5. Hierarchical Relational Learning for Few-Shot Knowledge Graph CompletionHan Wu, Jie Yin, Bala Rajaratnam, Jianyuan GuoICLR 2023 · 9 citations
Dusk over the sea between two cliffs drawn in fine vertical lines