We will begin by introducing structured prediction with various NLP examples. We will motivate the framework of Constrained Conditional Models using examples from sequential inference, sentence compression and semantic role labeling.
2. Applications of ILP Formulations in Natural Language Processing
Examples will be used to explain several of the key properties the framework offers. In particular, we will discuss several ways in which expressive constraints can be introduced into an application.
We will go over the following examples in this section:
- Co-reference resolution
- Information extraction
3. Modeling: Inference methods and Constraints
- Modeling problems as structured prediction problems
- The use of hard and soft constraints to represent prior knowledge.
- Augmenting Probabilistic Models with declarative constraints
- Inference Algorithms
4. Training Paradigms
- Structured learning
- Decomposed learning
5. Constraints Driven Learning
- Semi-supervised Learning with Constraints
- Constrained Expectation Maximization
- Learning with Indirect Supervision
6. Developing ILP based Applications
- A “template-based” approach” for developing applications with ILP formulations
- Software packages and tools
7. Looking ahead
Final words and looking ahead at structured Formulations in the neural network era