Qunar Tech Salon
Nov 29, 2015 · Artificial Intelligence
From Symbolic Semantics to Vector Representations: Deep Learning for Natural Language Understanding
The article reviews symbolic knowledge bases such as WordNet, ConceptNet and FrameNet, explains how deep learning replaces them with vector‑based semantic representations, and discusses encoder‑decoder RNNs, attention mechanisms, and future directions for truly understanding language through experiential learning.
Deep LearningNatural Language ProcessingRNN
0 likes · 12 min read