Symbolic, Distributed and Distributional Representations for Natural Language Processing in the Era of Deep Learning: a Survey
| Autor: | Fabio Massimo Zanzotto, Lorenzo Ferrone |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
compositional distributional semantic models Computer science Principle of compositionality lcsh:Mechanical engineering and machinery Review computer.software_genre Distributed representation lcsh:QA75.5-76.95 deep learning (DL) 68T05 68T50 Artificial Intelligence concatenative compositionality Fading lcsh:TJ1-1570 Robotics and AI Computer Science - Computation and Language Artificial neural network Settore INF/01 - Informatica I.2.6 business.industry I.2.7 Deep learning Computer Science Applications Human knowledge distributed representation compositionality natural language processing (NLP) Artificial intelligence lcsh:Electronic computers. Computer science business Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni Computation and Language (cs.CL) computer Natural language processing Natural language Intuition |
| Zdroj: | Frontiers in Robotics and AI, Vol 6 (2020) Frontiers in Robotics and AI |
| Popis: | Natural language is inherently a discrete symbolic representation of human knowledge. Recent advances in machine learning (ML) and in natural language processing (NLP) seem to contradict the above intuition: discrete symbols are fading away, erased by vectors or tensors called distributed and distributional representations. However, there is a strict link between distributed/distributional representations and discrete symbols, being the first an approximation of the second. A clearer understanding of the strict link between distributed/distributional representations and symbols may certainly lead to radically new deep learning networks. In this paper we make a survey that aims to renew the link between symbolic representations and distributed/distributional representations. This is the right time to revitalize the area of interpreting how discrete symbols are represented inside neural networks. 25 pages |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|