我们提出了一种系统推理的方法,该方法生产了基于事实基础的人类可解释的证明树。我们的解决方案类似于经典的基于序言的推理引擎的风格,在该引擎中,我们通过神经语言建模,指导生成和半磁头密集检索的结合来代替手工制作的规则。这款新颖的推理引擎Nellie动态实例化了可解释的推理规则,这些规则捕获和分数构成(DE)在自然语言陈述上。内莉(Nellie)在科学质量检查数据集上提供竞争性能,需要对多个事实进行结构化解释。
translated by 谷歌翻译
大型语言模型在各种问题答案(QA)基准测试方面取得了高度的性能,但其产出的解释性仍然难以捉摸。最近建议将结构化的解释称为“综合树”,以解释和检查质量检查系统的答案。为了更好地生成此类树木,我们提出了一种称为迭代检索生成推理​​器(IRGR)的架构。我们的模型能够通过系统地生成文本前提的分步解释来解释给定的假设。 IRGR模型迭代地搜索合适的场所,一次构建单个零件步骤。与以前的方法相反,我们的方法结合了生成步骤和房屋的检索,允许模型利用中间结论,并减轻基线编码器模型的输入大小限制。我们使用IntailmentBank数据集进行实验,在该数据集中,我们在前提检索和索引树上的现有基准优于现有的基准,总体正确性增长了约300%。
translated by 谷歌翻译
Pre-trained language models (LMs) have shown remarkable reasoning performance using explanations (or ``chain-of-thought'' (CoT)) for in-context learning. On the other hand, these reasoning tasks are usually presumed to be more approachable for symbolic programming. To make progress towards understanding in-context learning, we curate synthetic datasets containing equivalent (natural, symbolic) data pairs, where symbolic examples contain first-order logic rules and predicates from knowledge bases (KBs). Then we revisit neuro-symbolic approaches and use Language Models as Logic Programmer (LMLP) that learns from demonstrations containing logic rules and corresponding examples to iteratively reason over KBs, recovering Prolog's backward chaining algorithm. Comprehensive experiments are included to systematically compare LMLP with CoT in deductive reasoning settings, showing that LMLP enjoys more than 25% higher accuracy than CoT on length generalization benchmarks even with fewer parameters.
translated by 谷歌翻译
自动问题应答(QA)系统的目的是以时间有效的方式向用户查询提供答案。通常在数据库(或知识库)或通常被称为语料库的文件集合中找到答案。在过去的几十年里,收购知识的扩散,因此生物医学领域的新科学文章一直是指数增长。因此,即使对于领域专家,也难以跟踪域中的所有信息。随着商业搜索引擎的改进,用户可以在某些情况下键入其查询并获得最相关的一小组文档,以及在某些情况下从文档中的相关片段。但是,手动查找所需信息或答案可能仍然令人疑惑和耗时。这需要开发高效的QA系统,该系统旨在为用户提供精确和精确的答案提供了生物医学领域的自然语言问题。在本文中,我们介绍了用于开发普通域QA系统的基本方法,然后彻底调查生物医学QA系统的不同方面,包括使用结构化数据库和文本集合的基准数据集和几种提出的方​​法。我们还探讨了当前系统的局限性,并探索潜在的途径以获得进一步的进步。
translated by 谷歌翻译
知识基础问题回答(KBQA)旨在通过知识库(KB)回答问题。早期研究主要集中于回答有关KB的简单问题,并取得了巨大的成功。但是,他们在复杂问题上的表现远非令人满意。因此,近年来,研究人员提出了许多新颖的方法,研究了回答复杂问题的挑战。在这项调查中,我们回顾了KBQA的最新进展,重点是解决复杂问题,这些问题通常包含多个主题,表达复合关系或涉及数值操作。详细说明,我们从介绍复杂的KBQA任务和相关背景开始。然后,我们描述用于复杂KBQA任务的基准数据集,并介绍这些数据集的构建过程。接下来,我们提出两个复杂KBQA方法的主流类别,即基于语义解析的方法(基于SP)的方法和基于信息检索的方法(基于IR)。具体而言,我们通过流程设计说明了他们的程序,并讨论了它们的主要差异和相似性。之后,我们总结了这两类方法在回答复杂问题时会遇到的挑战,并解释了现有工作中使用的高级解决方案和技术。最后,我们结论并讨论了与复杂的KBQA有关的几个有希望的方向,以进行未来的研究。
translated by 谷歌翻译
讨论的现有账户强调了事先经验在解决新问题方面的作用。然而,大多数用于多跳文本推理的当代模型构建解释,考虑每个测试用例的隔离。众所周知,这种范式遭受语义漂移,这导致伪装解释的构建导致错误的结论。相比之下,我们研究了解释的多跳推断的绑架框架,该框架采用了在基于案例的推理中主要研究的检索重新使用修正范例。具体地,我们通过检索和调整来自类似训练示例的先前自然语言解释,提出了一种地址和解释了不均义推理问题的新颖框架。我们在下游致辞和科学推理任务上统一地评估了基于案例的绑架框架。我们的实验表明,与现有可说明的方法相比,所提出的框架可以有效地与稀疏和密集的预训练编码机制或下游变压器集成。此外,我们研究了检索重新使用 - 修改范例对可解释性和语义漂移的影响,表明它提高了构造解释的质量,从而提高了下游推理性能。
translated by 谷歌翻译
本文介绍了DIFF解释器,这是可解释的多跳推断的第一个混合框架,该框架通过可区分的凸优化将明确的约束与神经体系结构集成在一起。具体而言,DIFF解释器允许在受限的优化框架内微调神经表示,以回答和解释自然语言的多跳问题。为了证明混合框架的功效,我们将现有的基于ILP的求解器与基于变压器的表示相结合。对科学和常识性质量检查任务的广泛经验评估表明,在端到端可区分框架中明确约束的整合可以显着改善非不同可差异ILP求解器的性能(8.91%-13.3%)。此外,其他分析表明,与独立的变压器和以前的多跳方法相比,DIFF解释器能够实现强大的性能,同时仍提供结构化解释以支持其预测。
translated by 谷歌翻译
传统的象征性推理发动机,同时有吸引力的精度和可剥削性,具有一些主要缺点:使用依赖于逻辑术语的完全匹配(统一)的脆性推理程序的使用,无法应对不确定性,并需要对预调锋相同的需求规则基础(“知识获取”问题)。为了解决这些问题,我们设计了一个名为辫子的新颖逻辑推理,支持概率规则,并利用自定义统一功能和动态规则生成的概念来克服传统资料中普遍存在的脆性匹配和知识差距问题。在本文中,我们描述了编织中使用的推理算法,以及它们在基于分布式任务的框架中的实现,为输入查询构建证明/解释图。我们使用一个简单的QA示例来自儿童故事来激励辫子的设计,并解释各种组件如何共同努力,以产生一致的逻辑解释。最后,我们评估Roc Story Cloze测试的编织,并在提供基于帧的解释的同时实现近最先进的结果。
translated by 谷歌翻译
Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize external knowledge to assist LLMs. Unfortunately, current methods for incorporating external knowledge often require additional training or fine-tuning, which can be costly and may not be feasible for LLMs. To address this issue, we propose a novel post-processing approach, rethinking with retrieval (RR), which retrieves relevant external knowledge based on the decomposed reasoning steps obtained from the chain-of-thought (CoT) prompting. This lightweight approach does not require additional training or fine-tuning and is not limited by the input length of LLMs. We evaluate the effectiveness of RR through extensive experiments with GPT-3 on three complex reasoning tasks: commonsense reasoning, temporal reasoning, and tabular reasoning. Our results show that RR can produce more faithful explanations and improve the performance of LLMs.
translated by 谷歌翻译
Recent progress in pretraining language models on large textual corpora led to a surge of improvements for downstream NLP tasks. Whilst learning linguistic knowledge, these models may also be storing relational knowledge present in the training data, and may be able to answer queries structured as "fillin-the-blank" cloze statements. Language models have many advantages over structured knowledge bases: they require no schema engineering, allow practitioners to query about an open class of relations, are easy to extend to more data, and require no human supervision to train. We present an in-depth analysis of the relational knowledge already present (without fine-tuning) in a wide range of state-of-theart pretrained language models. We find that (i) without fine-tuning, BERT contains relational knowledge competitive with traditional NLP methods that have some access to oracle knowledge, (ii) BERT also does remarkably well on open-domain question answering against a supervised baseline, and (iii) certain types of factual knowledge are learned much more readily than others by standard language model pretraining approaches. The surprisingly strong ability of these models to recall factual knowledge without any fine-tuning demonstrates their potential as unsupervised open-domain QA systems. The code to reproduce our analysis is available at https: //github.com/facebookresearch/LAMA.
translated by 谷歌翻译
尽管在现代的机器学习算法的最新进展,其内在机制的不透明仍是采用的障碍。在人工智能系统灌输信心和信任,解释的人工智能已成为提高现代机器学习算法explainability的响应。归纳逻辑程序(ILP),符号人工智能的子场中,起着产生,因为它的直观的逻辑驱动框架的可解释的解释有希望的作用。 ILP有效利用绎推理产生从实例和背景知识解释的一阶分句理论。然而,在发展中通过ILP需要启发方法的几个挑战,在实践中他们的成功应用来解决。例如,现有的ILP系统通常拥有广阔的解空间,以及感应解决方案是对噪声和干扰非常敏感。本次调查总结在ILP的最新进展和统计关系学习和神经象征算法的讨论,其中提供给ILP协同意见。继最新进展的严格审查,我们划定观察的挑战,突出对发展不言自明的人工智能系统进一步ILP动机研究的潜在途径。
translated by 谷歌翻译
归纳逻辑编程(ILP)是一种机器学习的形式。ILP的目标是诱导推广培训示例的假设(一组逻辑规则)。随着ILP转30,我们提供了对该领域的新介绍。我们介绍了必要的逻辑符号和主要学习环境;描述ILP系统的构建块;比较几个维度的几个系统;描述四个系统(Aleph,Tilde,Aspal和Metagol);突出关键应用领域;最后,总结了未来研究的当前限制和方向。
translated by 谷歌翻译
从头开始解决复杂问题通常是有挑战性的,但如果我们可以访问其解决方案的其他类似问题,则更容易 - 一种称为基于案例的推理(CBR)的范式。我们提出了一种神经象征性的CBR方法(CBR-KBQA),用于在大知识库上应答。 CBR-KBQA由非参数内存组成,该内存存储案例(问题和逻辑表单)和参数模型,该参数模型可以通过检索与其相关的案例来为新问题生成逻辑表单。在包含复杂问题的几个KBQA数据集上,CBR-KBQA实现了竞争性能。例如,在ComplexWebQuestions数据集上,CBR-KBQA以11 \%的准确度优于当前最新状态。此外,我们表明CBR-KBQA能够使用新案例\ EMPH {没有}任何进一步的培训:通过在案例存储器中纳入一些人类标记的示例,CBR-KBQA能够成功地生成包含未经看线KB实体的逻辑表格以及关系。
translated by 谷歌翻译
Answering complex questions that require making latent decisions is a challenging task, especially when limited supervision is available. Recent works leverage the capabilities of large language models (LMs) to perform complex question answering in a few-shot setting by demonstrating how to output intermediate rationalizations while solving the complex question in a single pass. We introduce ``Successive Prompting'', where we iteratively break down a complex task into a simple task, solve it, and then repeat the process until we get the final solution. Successive prompting decouples the supervision for decomposing complex questions from the supervision for answering simple questions, allowing us to (1) have multiple opportunities to query in-context examples at each reasoning step (2) learn question decomposition separately from question answering, including using synthetic data, and (3) use bespoke (fine-tuned) components for reasoning steps where a large LM does not perform well. The intermediate supervision is typically manually written, which can be expensive to collect. We introduce a way to generate a synthetic dataset which can be used to bootstrap a model's ability to decompose and answer intermediate questions. Our best model (with successive prompting) achieves an improvement of ~5% absolute F1 on a few-shot version of the DROP dataset when compared with a state-of-the-art model with the same supervision.
translated by 谷歌翻译
象征性推理,基于规则的符号操作,是人类智慧的标志。然而,基于规则的系统的成功有限与基于学习的系统在外面的正式域之外的竞争中,例如自动定理证明。我们假设这是由于过去尝试中的规则的手动构建。在这项工作中,我们询问我们如何构建基于规则的系统,可以推理自然语言输入,但没有手动构建规则。我们提出了Metaqnl,这是一种“准自然”语言,可以表达正式逻辑和自然语言句子,并梅多斯诱惑,一种学习算法,它从训练数据组成的训练和答案,有或没有中间推理步骤。我们的方法在多个推理基准上实现了最先进的准确性;它学习具有更少数据的紧凑型号,不仅可以答案,而且产生答案。此外,对现实世界的形态学分析基准测试的实验表明,我们可以处理噪音和歧义。代码将在https://github.com/princeton-vl/metaqnl发布。
translated by 谷歌翻译
自然语言推理(NLI)任务通常需要通过多个步骤进行推理才能得出结论。尽管产生此类中间步骤的必要性(而不是摘要说明)获得了大众支持,但尚不清楚如何在不完全端到端的监督以及如何进一步利用此类步骤的情况下生成此类步骤。在这项工作中,我们训练一个序列到序列模型,仅生成下一步给定NLI前提和假设对(以及先前的步骤);然后通过外部知识和符号搜索来增强它,以仅在下一步监督下生成中间步骤。我们通过自动化和人类验证显示了此类生成的步骤的正确性。此外,我们表明,这种生成的步骤可以通过多个公共NLI数据集使用简单的数据增强策略来帮助提高端到端的NLI任务性能。
translated by 谷歌翻译
预训练的语言模型(PTLM)已显示出在自然语言任务上表现良好。许多先前的作品都以通过知识图(KGS)标记的关系链接的实体的形式利用结构性常识来协助PTLM。检索方法使用kg作为单独的静态模块,该模块限制了覆盖范围,因为kgs包含有限的知识。生成方法训练PTLMS kg三倍以提高获得知识的规模。但是,对符号KG实体的培训限制了其在涉及自然语言文本的任务中的适用性,在这些任务中,它们忽略了整体上下文。为了减轻这种情况,我们提出了一个以句子为条件的常识性上下文化器(COSE-CO)作为输入,以使其在生成与输入文本的整体上下文相关的任务中通常可用。为了训练Cose-Co,我们提出了一个新的数据集,其中包括句子和常识知识对。 COSE-CO推断出的知识是多种多样的,并且包含了基础KG中不存在的新实体。我们增强了在多选质量质量检查和开放式常识性推理任务中产生的知识,从而改善了CSQA,ARC,QASC和OBQA数据集的当前最佳方法。我们还展示了其在改善释义生成任务的基线模型方面的适用性。
translated by 谷歌翻译
有效的多跳问答(QA)需要在多个分散的段落上进行推理,并提供答案的解释。大多数现有方法无法提供可解释的推理过程,以说明这些模型如何得出答案。在本文中,我们提出了一种基于多跳QA的抽象含义表示形式(QDAMR)的问题分解方法,该方法通过将多跳问题分解为更简单的子问题并按顺序回答它们来实现可解释的推理。由于注释分解很昂贵,因此我们首先将理解多跳问题的复杂性委托给AMR解析器。然后,我们通过基于所需的推理类型对相应的AMR图进行分割实现多跳问题的分解。最后,我们使用AMR到文本生成模型生成子问题,并使用现成的QA模型回答它们。 HOTPOTQA的实验结果表明,我们的方法在可解释的推理方面具有竞争力,并且QDAMR产生的子问题是良好的,表现优于现有的基于问题分解的多跳质量质量检查方法。
translated by 谷歌翻译
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions; and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, and visual-language generation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.
translated by 谷歌翻译
The emergence of large pretrained models has enabled language models to achieve superior performance in common NLP tasks, including language modeling and question answering, compared to previous static word representation methods. Augmenting these models with a retriever to retrieve the related text and documents as supporting information has shown promise in effectively solving NLP problems in a more interpretable way given that the additional knowledge is injected explicitly rather than being captured in the models' parameters. In spite of the recent progress, our analysis on retriever-augmented language models shows that this class of language models still lack reasoning over the retrieved documents. In this paper, we study the strengths and weaknesses of different retriever-augmented language models such as REALM, kNN-LM, FiD, ATLAS, and Flan-T5 in reasoning over the selected documents in different tasks. In particular, we analyze the reasoning failures of each of these models and study how the models' failures in reasoning are rooted in the retriever module as well as the language model.
translated by 谷歌翻译