A Neural Architecture Mimicking Humans End-to-End for Natural Language Inference
This work addresses natural language inference for AI systems, but it is incremental as it builds on existing methods like LSTMs and attention.
The authors tackled natural language inference by proposing a neural architecture that mimics human reasoning, achieving state-of-the-art accuracy on the SNLI dataset.
In this work we use the recent advances in representation learning to propose a neural architecture for the problem of natural language inference. Our approach is aligned to mimic how a human does the natural language inference process given two statements. The model uses variants of Long Short Term Memory (LSTM), attention mechanism and composable neural networks, to carry out the task. Each part of our model can be mapped to a clear functionality humans do for carrying out the overall task of natural language inference. The model is end-to-end differentiable enabling training by stochastic gradient descent. On Stanford Natural Language Inference(SNLI) dataset, the proposed model achieves better accuracy numbers than all published models in literature.