StarSpace: Embed All The Things!

Abstract

We present StarSpace, a general-purpose neural embedding model that can solve a wide variety of problems: labeling tasks such as text classification, ranking tasks such as information retrieval/web search, collaborative filtering-based or content-based recommendation, embedding of multi-relational graphs, and learning word, sentence or document level embeddings. In each case the model works by embedding those entities comprised of discrete features and comparing them against each other -- learning similarities dependent on the task. Empirical results on a number of tasks show that StarSpace is highly competitive with existing methods, whilst also being generally applicable to new cases where those methods are not.

References in corpus (2)

• Text Understanding from Scratch
• Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers

Cited by in corpus (28)

• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• End-to-End Retrieval in Continuous Space
• Deep EHR: Chronic Disease Prediction Using Medical Notes
• DECAF: Deep Extreme Classification with Label Features
• Few-Shot Generalization Across Dialogue Tasks
• Cognitive Database: A Step towards Endowing Relational Databases with Artificial Intelligence Capabilities
• Vector representations of text data in deep learning
• Large-scale Collaborative Filtering with Product Embeddings
• Where is your field going? A Machine Learning approach to study the relative motion of the domains of Physics
• Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue
• Benchmarking neural embeddings for link prediction in knowledge graphs under semantic and structural changes
• A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots
• Graph Embeddings at Scale
• Modeling Intent, Dialog Policies and Response Adaptation for Goal-Oriented Interactions
• A Multilingual African Embedding for FAQ Chatbots
• Dividing the Ontology Alignment Task with Semantic Embeddings and Logic-based Modules
• Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank
• Explainable Prediction of Adverse Outcomes Using Clinical Notes
• Generating Interactive Worlds with Text
• BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining
• Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
• Furnishing Your Room by What You See: An End-to-End Furniture Set Retrieval Framework with Rich Annotated Benchmark Dataset
• Content Selection Network for Document-grounded Retrieval-based Chatbots
• Interactive Search and Exploration in Online Discussion Forums Using Multimodal Embeddings
• A Correlation Maximization Approach for Cross Domain Co-Embeddings
• The emergent algebraic structure of RNNs and embeddings in NLP
• Lightweight representation learning for efficient and scalable recommendation