KAAE: Numerical Reasoning for Knowledge Graphs via Knowledge-aware Attributes Learning
Numerical reasoning is pivotal in various artificial intelligence applications, such as natural language processing and recommender systems, where it involves using entities, relations, and attribute values (e.g., weight, length) to infer new factual relations (e.g., the Nile is longer than the Amaz...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Numerical reasoning is pivotal in various artificial intelligence
applications, such as natural language processing and recommender systems,
where it involves using entities, relations, and attribute values (e.g.,
weight, length) to infer new factual relations (e.g., the Nile is longer than
the Amazon). However, existing approaches encounter two critical challenges in
modeling: (1) semantic relevance-the challenge of insufficiently capturing the
necessary contextual interactions among entities, relations, and numerical
attributes, often resulting in suboptimal inference; and (2) semantic
ambiguity-the difficulty in accurately distinguishing ordinal relationships
during numerical reasoning, which compromises the generation of high-quality
samples and limits the effectiveness of contrastive learning. To address these
challenges, we propose the novel Knowledge-Aware Attributes Embedding model
(KAAE) for knowledge graph embeddings in numerical reasoning. Specifically, to
overcome the challenge of semantic relevance, we introduce a
Mixture-of-Experts-Knowledge-Aware (MoEKA) Encoder, designed to integrate the
semantics of entities, relations, and numerical attributes into a joint
semantic space. To tackle semantic ambiguity, we implement a new ordinal
knowledge contrastive learning (OKCL) strategy that generates high-quality
ordinal samples from the original data with the aid of ordinal relations,
capturing fine-grained semantic nuances essential for accurate numerical
reasoning. Experiments on three public benchmark datasets demonstrate the
superior performance of KAAE across various attribute value distributions. |
---|---|
DOI: | 10.48550/arxiv.2411.12950 |