III: Small: Collaborative Research: Explainable Natural Language Inference

III：小：协作研究：可解释的自然语言推理

• 批准号: 1815358
• 负责人: Niranjan Balasubramanian
• 金额: $ 24.45万
• 依托单位: SUNY at Stony Brook
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-01 至 2021-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1815358&HistoricalAwards=false
• 关键词: III; Small; Collaborative; Research; Explainable

Natural language inference (NLI) can support decision-making using information contained in natural language texts (e.g, detecting undiagnosed medical conditions in medical records, finding alternate treatments from scientific literature). This requires gathering facts extracted from text and reasoning over them. Current automated solutions for NLI are largely incapable of producing explanations for their inferences, but this capacity is essential for users to trust their reasoning in domains such as scientific discovery and medicine where the cost of making errors is high. This project develops natural language inference methods that are both accurate and explainable. They are accurate because they build on state-of-the-art deep learning frameworks which use powerful, automatically learned, representations of text. They are explainable because they aggregate information in units that can be represented in both a human readable explanation and a machine-usable vector representation. This project will advance methods in explainable natural language inference to enable the application of automated inference methods in critical domains such as medical knowledge extraction. The project will also evaluate the explainability of the inference decisions in collaboration with domain experts.This project reframes natural language inference as the task of constructing and reasoning over explanations. In particular, inference assembles smaller component facts into a graph (explanation graph) that it reasons over to make decisions. In this view, generating explanations is an integral part of the inference process and not a separate post-hoc mechanism. The project has three main goals: (a) Develop multiagent reinforcement learning models that can effectively and efficiently explore the space of explanation graphs, (b) Develop deep learning based aggregation mechanisms that can prevent inference from combining semantically incompatible evidence, and (c) Build a continuum of hypergraph based text representations that combine discrete forms of structured knowledge with their continuous embedding based representations. The techniques will be evaluated on three application domains: complex question answering, medical relation extraction, and clinical event detection from medical records. The results of the project will be disseminated through the project website, scholarly venues, and the software and datasets will be made available to the public.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

自然语言推理（NLI）可以使用自然语言文本中包含的信息来支持决策（例如，检测医疗记录中未诊断的医疗状况，从科学文献中寻找替代治疗方法）。这需要收集从文本中提取的事实并对其进行推理。目前NLI的自动化解决方案在很大程度上无法为他们的推理提供解释，但这种能力对于用户在科学发现和医学等领域信任他们的推理至关重要，因为这些领域的错误成本很高。该项目开发了既准确又可解释的自然语言推理方法。它们是准确的，因为它们建立在最先进的深度学习框架之上，这些框架使用强大的、自动学习的文本表示。它们是可解释的，因为它们将信息聚合在一起，可以用人类可读的解释和机器可用的矢量表示来表示。该项目将推进可解释的自然语言推理方法，使自动推理方法在医学知识提取等关键领域的应用成为可能。该项目还将与领域专家合作评估推理决策的可解释性。该项目将自然语言推理重新定义为构建和推理解释的任务。特别是，推理将更小的组成事实组装成一个图（解释图），它在上面进行推理以做出决策。在这种观点中，产生解释是推理过程的一个组成部分，而不是一个单独的事后机制。该项目有三个主要目标：（a）开发多智能体强化学习模型，可以有效地探索解释图的空间，（B）开发基于深度学习的聚合机制，可以防止推理组合语义不兼容的证据，以及（c）构建基于超图的文本表示的连续体，将联合收割机离散形式的结构化知识与其基于连续嵌入的表示相结合。这些技术将在三个应用领域进行评估：复杂问题回答，医疗关系提取和医疗记录中的临床事件检测。该项目的成果将通过项目网站、学术场所进行传播，软件和数据集将向公众开放。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension

• DOI: 10.18653/v1/2021.emnlp-main.490
• 发表时间: 2021-09
• 作者: Naoya Inoue;H. Trivedi;Steven K. Sinha;Niranjan Balasubramanian;Kentaro Inui

DeQA: On-Device Question Answering

• DOI: 10.1145/3307334.3326071
• 发表时间: 2019-06
• 期刊: Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services
• 作者: Qingqing Cao;Noah Weber;Niranjan Balasubramanian;A. Balasubramanian

Repurposing Entailment for Multi-Hop Question Answering Tasks

• DOI: 10.18653/v1/n19-1302
• 发表时间: 2019-04
• 期刊: ArXiv
• 作者: H. Trivedi;Heeyoung Kwon;Tushar Khot;Ashish Sabharwal;Niranjan Balasubramanian

Latent Part-of-Speech Sequences for Neural Machine Translation

• DOI: 10.18653/v1/d19-1072
• 发表时间: 2019-08
• 作者: Xuewen Yang;Yingru Liu;Dongliang Xie;Xin Wang;Niranjan Balasubramanian