[论文解读] A Question-Focused Multi-Factor Attention Network for Question Answering

Souvik Kundu, Hwee Tou Ng|arXiv (Cornell University)|Jan 25, 2018

Topic Modeling被引用 4

一句话总结

本文提出AMANDA，一种以问题为导向的多因素注意力网络，通过联合建模多句证据聚合与问题类型感知，增强了基于文档的问答性能。通过基于张量的多因素注意力机制与最大注意力问题编码，AMANDA在NewsQA、TriviaQA和SearchQA上实现了最先进性能，显著优于先前模型，其优势源于更深层次的推理与答案类型推理能力。

ABSTRACT

Neural network models recently proposed for question answering (QA) primarily focus on capturing the passage-question relation. However, they have minimal capability to link relevant facts distributed across multiple sentences which is crucial in achieving deeper understanding, such as performing multi-sentence reasoning, co-reference resolution, etc. They also do not explicitly focus on the question and answer type which often plays a critical role in QA. In this paper, we propose a novel end-to-end question-focused multi-factor attention network for answer extraction. Multi-factor attentive encoding using tensor-based transformation aggregates meaningful facts even when they are located in multiple sentences. To implicitly infer the answer type, we also propose a max-attentional question aggregation mechanism to encode a question vector based on the important words in a question. During prediction, we incorporate sequence-level encoding of the first wh-word and its immediately following word as an additional source of question type information. Our proposed model achieves significant improvements over the best prior state-of-the-art results on three large-scale challenging QA datasets, namely NewsQA, TriviaQA, and SearchQA.

研究动机与目标

• 解决现有问答模型在复杂推理任务中跨多句整合证据的局限性。
• 通过显式建模问题类型与关键问题词，改善答案类型对齐，提升答案抽取性能。
• 提升在开放世界问答数据集上的表现，要求超越简单跨度匹配的深层理解能力。
• 开发一个端到端框架，整合篇章-问题交互与答案类型推理，以提升泛化能力。

提出的方法

• 采用基于张量的多因素注意力机制，聚合多句中的有意义事实，实现多句推理与共指消解。
• 使用最大注意力问题聚合机制，识别并编码问题中最具信息量的词汇，用于答案类型推理。
• 在预测过程中，将首个wh-词及其后一个词的序列级表征作为问题类型的显式信号。
• 应用双向LSTM对篇章与问题表征进行编码，具备上下文感知能力。
• 结合预训练GloVe的词级嵌入与字符级CNN，提升OOV词处理能力。
• 采用指针网络，通过回归篇章中起始与结束位置来预测答案跨度。

实验结果

研究问题

• RQ1 多因素注意力机制能否有效整合多句证据，从而提升开放域问答中的推理能力？
• RQ2 聚焦关键问题词在多大程度上能改善答案类型对齐与预测准确率？
• RQ3 显式引入问题类型信号（如wh-词序列）在长篇与复杂答案上的性能提升程度如何？
• RQ4 所提出的模型是否在具有挑战性的开放世界问答基准上优于现有最先进方法？

主要发现

• AMANDA在三个大规模问答数据集（NewsQA、TriviaQA和SearchQA）上实现了最先进性能，优于所有先前发表的模型。
• 模型在F1与EM得分上均有显著提升，尤其在复杂、多句推理任务中表现突出。
• 在'why'和'other'问题类型以及更长答案上性能下降，表明长跨度边界预测仍具挑战。
• 错误分析显示，42%的失败源于答案歧义，22%源于上下文与问题词不匹配，10%源于复杂推理需求。
• 消融实验证实，多因素注意力与最大注意力问题编码组件对模型最优性能均至关重要。