Construction and Applications of Billion-Scale Pre-trained Multimodal Business Knowledge Graph

  title={Construction and Applications of Billion-Scale Pre-trained Multimodal Business Knowledge Graph},
  author={Shumin Deng and Chengming Wang and Zhoubo Li and Ningyu Zhang and Zelin Dai and Hehong Chen and Feiyu Xiong and Ming Yan and Qiang Chen and Mosha Chen and Jiaoyan Chen and Jeff Z. Pan and Bryan Hooi and Huajun Chen},
—Business Knowledge Graphs (KGs) are important to many enterprises today, providing factual knowledge and structured data that steer many products and make them more intelligent. Despite their promising benefits, building business KG necessitates solving prohibitive issues of deficient structure and multiple modalities. In this paper, we advance the understanding of the practical challenges related to building KG in non-trivial real-world systems. We introduce the process of building an open… 

A Concept Knowledge Graph for User Next Intent Prediction at Alipay

This paper proposes AlipayKG to explicitly characterize user intent, which is an offline concept knowledge graph in the Life-Service domain modeling the historical behaviors of users, the rich content interacted by users and the relations between them.

Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce

The task of supervised salience evaluation is formed, where given a CSK triple, the model is required to learn whether the triple is salient or not, and a simple but effective approach, PMI-tuning, is proposed, which shows promise for solving this novel problem.



Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules

This paper proposes a novel one, an explainable knowledge graph attention network that make prediction through modeling correlations between triples rather than purely relying on its head entity, relation and tail entity embeddings.

Billion-scale Pre-trained E-commerce Product Knowledge Graph Model

A Pre-trained Knowledge Graph Model (PKGM) is proposed for the authors' billion-scale e-commerce product knowledge graph, providing item knowledge services in a uniform way for embedding-based models without accessing triple data in the knowledge graph.

AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types

AutoKnow, the automatic (self-driving) system that addresses challenges of organizing information about products poses many additional challenges, including sparsity and noise of structured data for products, complexity of the domain with millions of product types and thousands of attributes, heterogeneity across large number of categories, as well as large and constantly growing number of products.

AliMeKG: Domain Knowledge Graph Construction and Application in E-commerce

AliMe KG, a domain knowledge graph in E-commerce that captures user problems, points of interest, item information and relations thereof, is proposed and its business value is demonstrated with several applications.

TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product Categories

This paper proposes TXtract, a taxonomy-aware knowledge extraction model that applies to thousands of product categories organized in a hierarchical taxonomy that is both scalable, as it trains a single model for thousands of categories, and effective, asIt extracts category-specific attribute values.

Product Knowledge Graph Embedding for E-commerce

The key entities are defined and summarize the pivotal product relations that are critical for general e-commerce applications including marketing, advertisement, search ranking and recommendation.

OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs

It is shown that expressive models significantly outperform simple scalable baselines, indicating an opportunity for dedicated efforts to further improve graph ML at scale.

KG-BERT: BERT for Knowledge Graph Completion

This work treats triples in knowledge graphs as textual sequences and proposes a novel framework named Knowledge Graph Bidirectional Encoder Representations from Transformer (KG-BERT) to model these triples.

AliCoCo2: Commonsense Knowledge Extraction, Representation and Application in E-commerce

Experimental results demonstrate that the proposed representation learning method achieves state-of-the-art performance on the task of knowledge graph completion (KGC), and applications on search and recommendation indicate great potential value of the construction and use of commonsense knowledge graph in e-commerce.

AliCG: Fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibaba

This paper proposes a framework called AliCG which is capable of extracting fine-grained concepts by a novel bootstrapping with alignment consensus approach, mining long-tail concepts with a novel low-resource phrase mining approach, and updating the graph dynamically via a concept distribution estimation method based on implicit and explicit user behaviors.