论文标题
QASEM解析：基于QA语义的文本到文本建模
QASem Parsing: Text-to-text Modeling of QA-based Semantics
论文作者
论文摘要
最近的一些作品建议将语义关系与问题和答案表示，将文本信息分解为单独的疑问自然语言陈述。在本文中，我们考虑了三个基于质量检查的语义任务 - 即QA -SRL，Qanom和Qadiscourse，每个任务都针对某种类型的预测 - 并建议将它们共同提供文本信息的全面表示。为了促进这一目标，我们研究了如何在半结构化输出的唯一设置中最好地利用序列到序列（SEQ2SEQ）预训练的语言模型，包括一组无序的问答对组合。我们检查了不同的输入和输出线性化策略，并评估多任务学习和简单数据增强技术在不平衡培训数据中的影响。因此，我们发布了第一个统一的QASEM解析工具，这对于可以从文本中的明确，基于质量检查的信息单位帐户中受益的下游应用程序实用。
Several recent works have suggested to represent semantic relations with questions and answers, decomposing textual information into separate interrogative natural language statements. In this paper, we consider three QA-based semantic tasks - namely, QA-SRL, QANom and QADiscourse, each targeting a certain type of predication - and propose to regard them as jointly providing a comprehensive representation of textual information. To promote this goal, we investigate how to best utilize the power of sequence-to-sequence (seq2seq) pre-trained language models, within the unique setup of semi-structured outputs, consisting of an unordered set of question-answer pairs. We examine different input and output linearization strategies, and assess the effect of multitask learning and of simple data augmentation techniques in the setting of imbalanced training data. Consequently, we release the first unified QASem parsing tool, practical for downstream applications who can benefit from an explicit, QA-based account of information units in a text.
