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.
翻译:自然语言推断(NLI)是一项具有挑战性的推理任务,它依赖于人类对语言和现实世界常识知识的共同理解。我们为NLI引入了一个新的模型,称为外部知识增强BERT(ExBERT),以外部知识来源的现实世界常识知识丰富背景代表性,并加强BERT的语言理解和推理能力。ExBERT充分利用了从BERT获得的背景文字表述,利用它们从知识图表中检索相关外部知识并编码检索到的外部知识。我们的模式适应了对投入进行推理所需的外部知识背景。关于挑战性SciTail和SNSLI基准的广泛实验表明ExBERT的有效性:与以往的状态相比,我们获得了SciTail的准确率95.9%和SnLI的准确率9.5%。