Created by Roya He (yunjie.he.17@ucl.ac.uk), this repository contains some informative papers and blogs on ML (Machine Learning) and NLP (Natural Language Processing). They are classified based on their themes. More interesting contents will be uploaded soon! Any recommendations are highly appreciated!
K-BERT: Enabling Language Representation with Knowledge Graph: fuse knowledge into the learned representation
EMBEDDING ENTITIES AND RELATIONS FOR LEARN- ING AND INFERENCE IN KNOWLEDGE BASES
A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
Learning Grounded Meaning Representations with Autoencoders
Blog: Multimodal Deep Learning
MMRFAN: Multi-modal Multi-relational Feature Aggregation Network for Medical Knowledge Representation Learning: maps entity's textual knowledge and visual knowledge into a unified space and learns representations.
Integrating Image-Based and Knowledge-Based Representation Learning: IKRL integrates image information and structured knowledge with TransE
Representation Learning of Knowledge Graphs with Entity Descriptions: DKRL integrates textual information and structured knowledge with TransE
A Multimodal Translation-Based Approach for Knowledge Graph Representation Learning: combining complementary(multimodal) energies is found making the results more robust. Total plausibilities referring to structured KGs, visual and textual information.
Explicit Knowledge-based Reasoning for Visual Question Answering
FVQA: Fact-based Visual Question Answering
Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual
Cross-Modal Knowledge Reasoning for Knowledge-based Visual Question Answering
Zero-shot Visual Question Answering using Knowledge Graphs
Multimodal Neural Graph Memory Networks for Visual Question Answering
Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources
Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering
Conceptbert: Concept-aware representation for visual question answering
Multi-Modal Answer Validation for Knowledge-Based VQA
Towards Knowledge-Augmented Visual Question Answering
Dynamic Memory Networks for Visual and Textual Question Answering
Adversarial Training Methods for Semi-Supervised Text Classification
Blog: Introduction to semi-supervised learning and adversarial training
OpenAI GPT-3 and Prompt Engineering
Improving Question Answering with External Knowledge
Cross-Lingual Machine Reading Comprehension
Few-Shot Question Answering by Pretraining Span Selection
Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering
Self-Supervised Knowledge Triplet Learning for Zero-Shot Question Answering
CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling