Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation
Not on the map. Why?
Abstract (arXiv)
Injecting textual information into knowledge graph (KG) entity representations has been a worthwhile expedition in terms of improving performance in KG oriented tasks within the NLP community. External knowledge often adopted to enhance KG embeddings ranges from semantically rich lexical dependency parsed features to a set of relevant key words to entire text descriptions supplied from an external corpus such as wikipedia and many more. Despite the gains this innovation (Text-enhanced KG embeddings) has made, the proposal in this work suggests that it can be improved even further. Instead of using a single text description (which would not sufficiently represent an entity because of the inherent lexical ambiguity of text), we propose a multi-task framework that jointly selects a set of text descriptions relevant to KG entities as well as align or augment KG embeddings with text descriptions. Different from prior work that plugs formal entity descriptions declared in knowledge bases, this framework leverages a retriever model to selectively identify richer or highly relevant text descriptions to use in augmenting entities. Furthermore, the framework treats the number of descriptions to use in augmentation process as a parameter, which allows the flexibility of enumerating across several numbers before identifying an appropriate number. Experiment results for Link Prediction demonstrate a 5.5% and 3.5% percentage increase in the Mean Reciprocal Rank (MRR) and Hits@10 scores respectively, in comparison to text-enhanced knowledge graph augmentation methods using traditional CNNs.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 41 references that are in the map. First posted on arXiv 28 Jul 2023.
Builds on
23 of 41 references.
References · 23
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2019Language Models as Knowledge Bases?cited by 1,936
- 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
- 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
- 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
- 2016Complex Embeddings for Simple Link Predictioncited by 902
- 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
- 2019KG-BERT: BERT for Knowledge Graph Completioncited by 324
11 more
- 2020Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Poolingcited by 115
- 2020Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queriescited by 107
- 2019GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledgecited by 79
- 2020Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoderscited by 61
- 2020UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System Metathesauruscited by 53
- 2022A Decade of Knowledge Graphs in Natural Language Processing: A Surveycited by 40
- 2021Improving Biomedical Pretrained Language Models with Knowledgecited by 36
- 2013Connecting Language and Knowledge Bases with Embedding Models for Relation Extractioncited by 21
- 2018Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMscited by 14
- 2022Position-based Prompting for Health Outcome Generationcited by 7
- 2021Detect and Classify -- Joint Span Detection and Classification for Health Outcomescited by 6
Built on by
Citing papers per year: 2025: 1.
1 paper.