arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.06187cs.CLcs.LO
收藏

NLProlog:弱统一推理在自然语言问答中的应用

NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language

University College London(伦敦大学学院)

Leon Weber, Pasquale Minervini, Jannes Münchmeyer, Ulf Leser, Tim Rocktäschel

摘要:

基于规则的模型对各种任务都有吸引力,因为它们本质上导致可解释和可解释的决策,并且可以很容易地结合先验知识。然而,这样的系统是难以适用于涉及自然语言的问题,由于其语言的可变性。相比之下,神经模型可以通过从数据中学习单词及其组成的分布式表示来很好地应对歧义,但会导致难以解释的模型。在本文中,我们描述了一种新的方式解决多跳推理任务的自然语言的神经网络与逻辑编程相结合的模型。具体来说,我们建议使用Prolog证明器,我们扩展到利用预训练的句子编码器的相似性函数。我们通过反向传播来微调相似性函数的表示。这导致了一个系统,可以应用基于规则的推理自然语言,并从训练数据诱导特定领域的规则。我们在两个不同的问答任务上评估了所提出的系统,表明它优于两个基线- BIDAF(Seo等人,2016 a)和FAST QA(Weissenborn等人,2017 b),并在MedHop数据集上取得了有竞争力的结果(Welbl et al.,2017年)。

英文摘要:

Rule-based models are attractive for various tasks because they inherently lead to interpretable and explainable decisions and can easily incorporate prior knowledge. However, such systems are difficult to apply to problems involving natural language, due to its linguistic variability. In contrast, neural models can cope very well with ambiguity by learning distributed representations of words and their composition from data, but lead to models that are difficult to interpret. In this paper, we describe a model combining neural networks with logic programming in a novel manner for solving multi-hop reasoning tasks over natural language. Specifically, we propose to use a Prolog prover which we extend to utilize a similarity function over pretrained sentence encoders. We fine-tune the representations for the similarity function via backpropagation. This leads to a system that can apply rule-based reasoning to natural language, and induce domain-specific rules from training data. We evaluate the proposed system on two different question answering tasks, showing that it outperforms two baselines -- BIDAF (Seo et al., 2016a) and FAST QA (Weissenborn et al., 2017b) on a subset of the WikiHop corpus and achieves competitive results on the MedHop data set (Welbl et al., 2017).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑