Solving Hard Analogy Questions with Relation Embedding Chains

Nitesh Kumar, Steven Schockaert
10/18/2023
cs.CLcs.AI

No confident code implementation found for this paper.

Abstract

Modelling how concepts are related is a central topic in Lexical Semantics. A common strategy is to rely on knowledge graphs (KGs) such as ConceptNet, and to model the relation between two concepts as a set of paths. However, KGs are limited to a fixed set of relation types, and they are incomplete and often noisy. Another strategy is to distill relation embeddings from a fine-tuned language model. However, this is less suitable for words that are only indirectly related and it does not readily allow us to incorporate structured domain knowledge. In this paper, we aim to combine the best of both worlds. We model relations as paths but associate their edges with relation embeddings. The paths are obtained by first identifying suitable intermediate words and then selecting those words for which informative relation embeddings can be obtained. We empirically show that our proposed representations are useful for solving hard analogy questions.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

RelBERT: Embedding Relations with Language Models

86% match1 repo482023

Message Intercommunication for Inductive Relation Reasoning

82% match2023

Entity or Relation Embeddings? An Analysis of Encoding Strategies for Relation Extraction

82% match1 repo22023

Explainable Representations for Relation Prediction in Knowledge Graphs

82% match1 repo32023

From Symbolic to Natural-Language Relations: Rethinking Knowledge Graph Construction in the Era of Large Language Models

82% match2026

Relation Geometry in Semantic Space of Language Models

82% match2026

Cite this paper

@article{kumar2023solving,
  title  = {Solving Hard Analogy Questions with Relation Embedding Chains},
  author = {Nitesh Kumar and Steven Schockaert},
  year   = {2023},
  eprint = {2310.12379},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.12379v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.12379.svg)](https://codeofpaper.com/paper/2310.12379)

Discussion