Difference between revisions of "Neural Coreference"
m (BPeat moved page Neural Coreference Resolution to Neural Coreference without leaving a redirect) |
|||
| Line 8: | Line 8: | ||
<youtube>rpwEWLaueRk</youtube> | <youtube>rpwEWLaueRk</youtube> | ||
| + | <youtube>2OkvUVwokHM</youtube> | ||
| + | <youtube>3MjIkWxXigM</youtube> | ||
| + | <youtube>xYfkPVbrae0</youtube> | ||
| + | <youtube>pyr1hRv8Yag</youtube> | ||
Revision as of 16:44, 25 May 2018
- Deep Reinforcement Learning
- State-of-the-art neural coreference resolution for chatbots
- Try the demo - type in your sentence
Coreference is the fact that two or more expressions in a text – like pronouns or nouns – link to the same person or thing. It is a classical Natural language processing task, that has seen a revival of interest in the past two years as several research groups applied cutting-edge deep-learning and reinforcement-learning techniques to it. It is also one of the key building blocks to building conversational Artificial intelligences.
