Attention Mechanism-based Text Matching: Enhanced LSTM
Natural Language Inference (NLI) is concerned with determining whether a natural language hypothesis can be inferred (entailed) from a premise. Bi-directional Attention Mechanism.
Illustration of high-level Model Architecture
Reference
- Enhanced LSTM for Natural Language Inference https://arxiv.org/pdf/1609.06038v3.pdf
- Reasoning about Entailment with Neural Attention https://arxiv.org/pdf/1509.06664v1.pdf
TO-RUN:
Training：python train.py
Testing: python test.py