Heterogeneous Graph Neural Networks for Concept Prerequisite Relation Learning in Educational Data (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to learn prerequisite relations among concepts are lacking . concepts are crucial for learning, organizing, applying and generating knowledge . |
| Approach: | They propose a concept prerequisite relation learning approach which combines concept representation and concept pairwise features to make it more practical. |
| Outcome: | The proposed method achieves state-of-the-art results on four datasets. |
Similar Papers
R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning (2020.coling-main)
Copied to clipboard
| Challenge: | Concept prerequisite chain learning is an unsupervised task with no access to labeled concept pairs during training. |
| Approach: | They propose a model that uses deep learning representations to predict concept relations . they frame concept prerequisite chain learning as an unsupervised task with no labeled concept pairs . |
| Outcome: | The proposed model outperforms semi-supervised methods in terms of accuracy and F1 score. |
Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods to learn prerequisite relations between concepts require annotated concept pairs during training. |
| Approach: | They propose to use an optimized variational graph autoencoder to learn prerequisite chains in unsupervised manner using an information-rich domain and an information poor domain. |
| Outcome: | The proposed model learns to transfer concept prerequisite relations from an information-rich domain (source domain) to an information poor domain (target domain) the annotated data and resources as well as the code will be made publicly available. |
A Novel Table-to-Graph Generation Approach for Document-Level Joint Entity and Relation Extraction (2023.acl-long)
Copied to clipboard
| Challenge: | Existing document-level relation extraction methods assume entities and their mentions are given beforehand, which is inadequate for real-world applications. |
| Approach: | They propose a table-to-graph generation model for joint extraction of entities and relations at document-level. |
| Outcome: | The proposed model surpasses existing methods by a large margin and achieves state-of-the-art results on a document-level relation extraction dataset. |
Generic and Trend-aware Curriculum Learning for Relation Extraction (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing curriculum learning approaches for relation extraction are lacking in text graphs. |
| Approach: | They propose a generic and trend-aware curriculum learning approach that integrates textual and structural information in text graphs for relation extraction between entities. |
| Outcome: | The proposed model shows improvement over state-of-the-art methods across several datasets. |
Jointly Learning Entity and Relation Representations for Entity Alignment (D19-1)
Copied to clipboard
| Challenge: | Entity alignment is a viable method for integrating heterogeneous knowledge among different knowledge graphs (KGs). |
| Approach: | They propose a Graph Convolutional Network-based framework for learning relation representations by embedding relation seeds into entities and incorporating relation approximation into entities to iteratively improve alignment. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on three real-world cross-lingual datasets. |
Pretraining Language Models with Text-Attributed Heterogeneous Graphs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing pretraining tasks for Language Models (LMs) focus on learning the textual information of each entity and overlook the crucial aspect of capturing topological connections among entities in TAHGs. |
| Approach: | They propose a topology-aware pretraining task that explicitly considers the topological and heterogeneous information in TAHGs by optimizing an LM and an auxiliary heterogenous graph neural network. |
| Outcome: | The proposed framework explicitly considers the topological and heterogeneous information in TAHGs. |
Self-Attention Enhanced CNNs and Collaborative Curriculum Learning for Distantly Supervised Relation Extraction (D19-1)
Copied to clipboard
| Challenge: | Distantly Supervised Relation Extraction (DSRE) suffers from mislabelled data . human annotation on large datasets is costly and often impossible . |
| Approach: | They propose a model that employs a collaborative curriculum learning framework to reduce mislabelled data. |
| Outcome: | The proposed model outperforms baselines including state-of-the-art in terms of P@N and PR curve metrics on a widely-used public dataset. |
DynGL-SDP: Dynamic Graph Learning for Semantic Dependency Parsing (2022.coling-1)
Copied to clipboard
| Challenge: | Existing parsers that learn graph representations based on static graphs are error-prone and disjointed . Graph-based parser can parse sentences efficiently but suffer from error propagation . |
| Approach: | They propose a dynamic graph learning framework to learn graph representations based on a static graph constructed by an existing parser. |
| Outcome: | The proposed parser outperforms the previous parsers on the SemEval-2015 task 18 dataset in three languages. |
LinkNBed: Multi-Graph Representation Learning with Entity Linkage (P18-1)
Copied to clipboard
| Challenge: | Knowledge graphs have emerged as an important model for studying complex multi-relational data. |
| Approach: | They propose a deep relational learning framework that learns entity and relationship representations across multiple graphs. |
| Outcome: | The proposed framework improves on the state-of-the-art relational learning approaches and identifies entity linkage across graphs. |
Learning Relatedness between Types with Prototypes for Relation Extraction (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing datasets have no intrinsic Ontology for relation types. |
| Approach: | They propose to use prototypical examples to represent each relation type and use them to augment related types from a different dataset. |
| Outcome: | The proposed model improves on a baseline with multi-task learning between datasets to obtain better representation for relations. |