Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference
arXiv:1904.12104
Abstract
Natural language inference (NLI) is among the most challenging tasks in natural language understanding. Recent work on unsupervised pretraining that leverages unsupervised signals such as language-model and sentence prediction objectives has shown to be very effective on a wide range of NLP problems. It would still be desirable to further understand how it helps NLI; e.g., if it learns artifacts in data annotation or instead learn true inference knowledge. In addition, external knowledge that does not exist in the limited amount of NLI training data may be added to NLI models in two typical ways, e.g., from human-created resources or an unsupervised pretraining paradigm. We runs several experiments here to investigate whether they help NLI in the same way, and if not,how?
References in corpus (6)
- Enhanced LSTM for Natural Language Inference
- Neural Natural Language Inference Models Enhanced with External Knowledge
- Enhancing Sentence Embedding with Generalized Pooling
- Stress Test Evaluation for Natural Language Inference
- Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence Embedding
- Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering