• Corpus ID: 244954479

Semantic TrueLearn: Using Semantic Knowledge Graphs in Recommendation Systems

@article{Bulathwela2021SemanticTU,
  title={Semantic TrueLearn: Using Semantic Knowledge Graphs in Recommendation Systems},
  author={Sahan Bulathwela and Mar'ia P'erez-Ortiz and Emine Yilmaz and John Shawe-Taylor},
  journal={ArXiv},
  year={2021},
  volume={abs/2112.04368}
}
In informational recommenders, many challenges arise from the need to handle the semantic and hierarchical structure between knowledge areas. This work aims to advance towards building a state-aware educational recommendation system that incorporates semantic relatedness between knowledge topics, propagating latent information across semantically related topics. We introduce a novel learner model that exploits this semantic relatedness between knowledge components in learning resources using… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 32 REFERENCES
On Computing Entity Relatedness in Wikipedia, with Applications
TrueLearn: A Family of Bayesian Algorithms to Match Lifelong Learners to Open Educational Resources
TLDR
This work uses a text ontology based on Wikipedia to automatically extract knowledge components of educational resources and proposes a set of online Bayesian strategies inspired by the well-known areas of item response theory and knowledge tracing, which show clear promise towards building an effective educational recommendation system.
Towards an Integrative Educational Recommender for Lifelong Learners
TLDR
This work attempts to build a novel educational recommender, that relies on an integrative approach combining multiple drivers of learners engagement, and achieves promising performance while retaining a human interpretable learner model.
Graph-based Knowledge Tracing: Modeling Student Proficiency Using Graph Neural Network
TLDR
Empirical validations indicated that the proposed GNN-based knowledge tracing method could potentially improve the prediction of student performance and demonstrated more interpretable predictions compared to those of the previous methods, without the requirement of any additional information.
What's in it for me?: Augmenting Recommended Learning Resources with Navigable Annotations
TLDR
An interface that enables the user to quickly identify relevant fragments within multiple long documents that relies on a machine-generated layer of annotations that reveals the coverage of topics per fragment and document is introduced.
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
TLDR
A general-purpose fine-tuning recipe for retrieval-augmented generation (RAG) -- models which combine pre-trained parametric and non-parametric memory for language generation, and finds that RAG models generate more specific, diverse and factual language than a state-of-the-art parametric-only seq2seq baseline.
PEEK: A Large Dataset of Learner Engagement with Educational Videos
TLDR
A large and novel dataset of learners engaging with educational videos in-the-wild, named Personalised Educational Engagement with Knowledge Topics (PEEK), is released, one of the first publicly available datasets that address personalised educational engagement.
RKT: Relation-Aware Self-Attention for Knowledge Tracing
TLDR
A novel Relation-aware self-attention model for Knowledge Tracing that outperforms state-of-the-art knowledge tracing methods and interpretable attention weights help visualize the relation between interactions and temporal patterns in the human learning process.
Transparent, Scrutable and Explainable User Models for Personalized Recommendation
TLDR
This paper presents a new set-based recommendation technique that permits the user model to be explicitly presented to users in natural language, empowering users to understand recommendations made and improve the recommendations dynamically.
Transforming Wikipedia into an Ontology-based Information Retrieval Search Engine for Local Experts using a Third-Party Taxonomy
TLDR
The technique, though presented here as a way to identify local experts, is generic, in that any third party taxonomy can be used in this to connect Wikipedia to any non-Wikipedia data source.
...
...