Learning in Text Streams: Discovery and Disambiguation of Entity and Relation Instances
| Autor: | Giuseppe Marra, Andrea Zugarini, Stefano Melacci, Marco Maggini |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Relation (database) Computer Networks and Communications Computer science media_common.quotation_subject Machine Learning (stat.ML) 02 engineering and technology computer.software_genre Machine Learning (cs.LG) Data modeling Knowledge-based systems Machine learning natural language processing (NLP) recurrent neural networks Statistics - Machine Learning Artificial Intelligence Reading (process) 0202 electrical engineering electronic engineering information engineering Set (psychology) media_common Computer Science - Computation and Language business.industry Computer Science Applications Knowledge base Identity (object-oriented programming) Encyclopedia 020201 artificial intelligence & image processing Artificial intelligence business Computation and Language (cs.CL) computer Software Natural language processing |
| Zdroj: | IEEE Transactions on Neural Networks and Learning Systems. 31:4475-4486 |
| ISSN: | 2162-2388 2162-237X |
| Popis: | We consider a scenario where an artificial agent is reading a stream of text composed of a set of narrations, and it is informed about the identity of some of the individuals that are mentioned in the text portion that is currently being read. The agent is expected to learn to follow the narrations, thus disambiguating mentions and discovering new individuals. We focus on the case in which individuals are entities and relations, and we propose an end-to-end trainable memory network that learns to discover and disambiguate them in an online manner, performing one-shot learning, and dealing with a small number of sparse supervisions. Our system builds a not-given-in-advance knowledge base, and it improves its skills while reading unsupervised text. The model deals with abrupt changes in the narration, taking into account their effects when resolving co-references. We showcase the strong disambiguation and discovery skills of our model on a corpus of Wikipedia documents and on a newly introduced dataset, that we make publicly available. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|