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 name 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 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.
Anthology ID:
2022.findings-emnlp.184
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2498–2509
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.184
DOI:
10.18653/v1/2022.findings-emnlp.184
Bibkey:
Cite (ACL):
Mingchen Li, Junfan Chen, Samuel Mensah, Nikolaos Aletras, Xiulong Yang, and Yang Ye. 2022. A Hierarchical N-Gram Framework for Zero-Shot Link Prediction. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2498–2509, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
A Hierarchical N-Gram Framework for Zero-Shot Link Prediction (Li et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2022.findings-emnlp.184.pdf
PDF Search