mlsanityData to 7 Oct 2026

Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations

arXiv 2104.02667 ↗First posted 6 Apr 2021cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

The growing popularity of Virtual Assistants poses new challenges for Entity Resolution, the task of linking mentions in text to their referent entities in a knowledge base. Specifically, in the shopping domain, customers tend to use implicit utterances (e.g., "organic milk") rather than explicit names, leading to a large number of candidate products. Meanwhile, for the same query, different customers may expect different results. For example, with "add milk to my cart", a customer may refer to a certain organic product, while some customers may want to re-order products they regularly purchase. To address these issues, we propose a new framework that leverages personalized features to improve the accuracy of product ranking. We first build a cross-source heterogeneous knowledge graph from customer purchase history and product knowledge graph to jointly learn customer and product embeddings. After that, we incorporate product, customer, and history representations into a neural reranking model to predict which candidate is most likely to be purchased for a specific customer. Experiments show that our model substantially improves the accuracy of the top ranked candidates by 24.6% compared to the state-of-the-art product search model.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 25 of its 57 references that are in the map. First posted on arXiv 6 Apr 2021.

Builds on

25 of 57 references.

References · 25

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  4. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  5. 2017Neural Collaborative Filteringcited by 1,108
  6. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  7. 2016Complex Embeddings for Simple Link Predictioncited by 897
  8. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  9. 2019Heterogeneous Graph Attention Networkcited by 732
  10. 2020Heterogeneous Graph Transformercited by 581
  11. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 197
  12. 2019Zero-Shot Entity Linking by Reading Entity Descriptionscited by 124
13 more
  1. 2019Learning Dense Representations for Entity Retrievalcited by 122
  2. 2019Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systemscited by 107
  3. 2020Heterogeneous Graph Neural Networks for Malicious Account Detectioncited by 95
  4. 2018End-to-End Neural Entity Linkingcited by 85
  5. 2019Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendationcited by 70
  6. 2015Reasoning about Entailment with Neural Attentioncited by 68
  7. 2018Characterizing and Detecting Hateful Users on Twittercited by 55
  8. 2019Semantic Product Searchcited by 51
  9. 2018Neural Collective Entity Linkingcited by 21
  10. 2017Neural Cross-Lingual Entity Linkingcited by 15
  11. 2015Multi-Modal Bayesian Embeddings for Learning Social Knowledge Graphscited by 5
  12. 2020Entity Linking via Dual and Cross-Attention Encoderscited by 4
  13. 2020Learning Robust Models for e-Commerce Product Searchcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3.

4 papers.

  1. 2023Large Language Models on Graphs: A Comprehensive Surveycited by 190
  2. 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackcited by 86
  3. 2023Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verificationcited by 19
  4. 2022"Does it come in black?" CLIP-like models are zero-shot recommenderscited by 4