GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
Explore this paper's citation graph
Summary
This work explores the possibility of learning generic latent relational graphs that capture dependencies between pairs of data units from large-scale unlabeled data and transferring the graphs to downstream tasks, and shows that the learned graphs are generic enough to be transferred to different embeddings on which the graphs have been trained.
- Type
- preprint
- Published
- 2018-06-14
- Cited by
- 36
- References
- 52
- Access
- Open access
- OpenAlex
- https://openalex.org/W2808344987
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:49212145
Keywords
Computer science, Mathematics
References
- Parsing Natural Scenes and Natural Language with Recursive Neural Networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- A large annotated corpus for learning natural language inference
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
- Long Short-Term Memory
- Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
- ImageNet: A large-scale hierarchical image database
- Learning Word Vectors for Sentiment Analysis
- The Graph Neural Network Model
- ImageNet Large Scale Visual Recognition Challenge
- Distributed Representations of Words and Phrases and their Compositionality
- Deep Residual Learning for Image Recognition
- GloVe: Global Vectors for Word Representation
- Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
- Pixel Recurrent Neural Networks
- Virtual Adversarial Training for Semi-Supervised Text Classification
- Designing Neural Network Architectures using Reinforcement Learning
- Learning to Compose Words into Sentences with Reinforcement Learning
- A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Cited by
- CoNet: Collaborative Cross Networks for Cross-Domain Recommendation
- Improving Question Answering by Commonsense-Based Pre-Training
- Learning Distributed Representations of Symbolic Structure Using Binding and Unbinding Operations
- SpaMHMM: Sparse Mixture of Hidden Markov Models for Graph Connected Entities
- Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
- Drone Detection and Pose Estimation Using Relational Graph Networks
- IMHO Fine-Tuning Improves Claim Detection
- Data-Efficient Graph Embedding Learning for PCB Component Detection
- SpotTune: Transfer Learning Through Adaptive Fine-Tuning
- Graph Reasoning Networks for Visual Question Answering
- Non-Local Recurrent Neural Memory for Supervised Sequence Modeling
- Domain Adaptation for Person-Job Fit with Transferable Deep Global Match Network
- Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs
- A Simple Recurrent Unit with Reduced Tensor Product Representations
- Learning to Generalize via Self-Supervised Prediction
- Two-Headed Monster and Crossed Co-Attention Networks
- Graph Interaction Networks for Relation Transfer in Human Activity Videos
- Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games
- SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
- Unsupervised urban scene segmentation via domain adaptation
Related papers
- ИСПОЛЬЗОВAНИЕ ПОТЕНЦИAЛA СОЦИAЛЬНЫХ ПAРТНЕРОВ В ПОДГОТОВКЕ БУДУЩИХ ПЕДAГОГОВ
- Primärzerlegung in Steinschen Algebren
- Über unirationale Scharen auf algebraischen Mannigfaltigkeiten
- Produkttreue Klassen universeller Algebren
- Approximation of fixed points of multifunctions in partial metric spaces
- The World of Jagdish N. Srivastava
- Kennzeichnung derp-adischen und der endlichen algebraischen Zahlkörper
- Algebraic varieties with automorphism groups of maximal rank
- Kohomologie vonp-Lie-Algebren