ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference
This addresses the challenge of commonsense reasoning in NLI for AI applications, representing an incremental improvement by integrating external knowledge into an existing model.
The paper tackled the problem of neural language models lacking commonsense knowledge for Natural Language Inference (NLI) by introducing ExBERT, which enhances BERT with external knowledge, achieving accuracies of 95.9% on SciTail and 91.5% on SNLI.
Neural language representation models such as BERT, pre-trained on large-scale unstructured corpora lack explicit grounding to real-world commonsense knowledge and are often unable to remember facts required for reasoning and inference. Natural Language Inference (NLI) is a challenging reasoning task that relies on common human understanding of language and real-world commonsense knowledge. We introduce a new model for NLI called External Knowledge Enhanced BERT (ExBERT), to enrich the contextual representation with real-world commonsense knowledge from external knowledge sources and enhance BERT's language understanding and reasoning capabilities. ExBERT takes full advantage of contextual word representations obtained from BERT and employs them to retrieve relevant external knowledge from knowledge graphs and to encode the retrieved external knowledge. Our model adaptively incorporates the external knowledge context required for reasoning over the inputs. Extensive experiments on the challenging SciTail and SNLI benchmarks demonstrate the effectiveness of ExBERT: in comparison to the previous state-of-the-art, we obtain an accuracy of 95.9% on SciTail and 91.5% on SNLI.