Papers by Nicolas Pröllochs
Learning Interpretable Negation Rules via Weak Supervision at Document Level: A Reinforcement Learning Approach (N19-1)
Copied to clipboard
| Challenge: | Negation scope detection is a supervised learning task which relies on negation labels at word level. |
| Approach: | They propose a method that replaces world-level negation labels with document-level sentiment annotations. |
| Outcome: | The proposed approach eliminates the need for world-level negation labels and replaces it with document-level sentiment annotations. |