Discriminative Learning over Constrained Latent Representations
Focus: Binary classification tasks that require an intermediate representation
General recipe for NLP problems: "Learning over Constrained Latent Representations" (LCLR)
Example domains: transliteration,
Example task: paraphrase identification. Given two sentences, are they a paraphrase of each other? It's a binary decision, but we need a complex intermediate representation. In this case, we use an alignment.
The intermediate representation is a latent representation that allows us to justify a positive (negative) label.
Prior Work
Two-stage approach:
- Generate an intermediate representation (fixed)
- Extract features based on the intermediate representation
- Use those features for learning
Problem: the intermediate representation doesn't know about the binary task; joint model would potentially give us a better intermediate rep
LCLR
- Jointly learns the intermediate representation and the labels
- Constraint-based inference for the intermediate representation
- Uses Integer Linear Programming on latent variables
What we want from the intermediate representation:
- Only positive examples have good intermediate representations.
- No negative example has a good intermediate representation.
For positive example :
For negative example :
So the prediction function is: