Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference
This work addresses the challenge of improving NLI models for NLP researchers, but it appears incremental as it focuses on understanding existing methods rather than introducing new ones.
The paper investigates how unsupervised pretraining and external knowledge sources affect natural language inference (NLI), aiming to determine if they learn true inference knowledge or data artifacts, but does not report specific numerical results.
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?