Using Semantic Similarity as Reward for Reinforcement Learning in Sentence Generation.
Go YasuiYoshimasa TsuruokaMasaaki NagataPublished in: ACL (2) (2019)
Keyphrases
- semantic similarity
- reinforcement learning
- sentence similarity
- co occurrence
- semantic content
- similarity measure
- wordnet
- semantically similar
- semantic information
- semantic similarity computation
- semantic features
- vector space model
- state space
- reinforcement learning algorithms
- semantic similarity measure
- learning algorithm
- natural language
- semantic relatedness
- machine learning
- cosine similarity
- text summarization
- word sense disambiguation
- semantic relationships
- optimal policy
- visual similarity
- learning agent
- average reward
- metadata
- database