Implicit arguments, which cannot be detected solely through syntactic cues,
make it harder to extract predicate-argument tuples. We present a new model for
implicit argument prediction that draws on reading comprehension, casting the
predicate-argument tuple with the missing argument as a query. We also draw on
pointer networks and multi-hop computation. Our model shows good performance on
an argument cloze task as well as on a nominal implicit argument prediction
task.

通过阅读理解、指针网络和多跳计算，提出了一种新的模型来预测隐式参数，该模型良好地完成了隐式参数预测任务。

阅读理解中的隐含参数预测

Implicit Argument Prediction as Reading Comprehension

Implicit arguments are not syntactically connected to their predicates, and
are therefore hard to extract. Previous work has used models with large numbers
of features, evaluated on very small datasets. We propose to train models for
implicit argument prediction on a simple cloze task, for which data can be
generated automatically at scale. This allows us to use a neural model, which
draws on narrative coherence and entity salience for predictions. We show that
our model has superior performance on both synthetic and natural data.

通过简单的 cloze 任务训练神经模型，提高了隐式论证预测性能，该模型利用叙事连贯性和实体显著性进行预测。

利用事件知识进行隐式论证预测

Implicit Argument Prediction with Event Knowledge

We introduce Question-Answer Meaning Representations (QAMRs), which represent
the predicate-argument structure of a sentence as a set of question-answer
pairs. We also develop a crowdsourcing scheme to show that QAMRs can be labeled
with very little training, and gather a dataset with over 5,000 sentences and
100,000 questions. A detailed qualitative analysis demonstrates that the
crowd-generated question-answer pairs cover the vast majority of
predicate-argument relationships in existing datasets (including PropBank,
NomBank, QA-SRL, and AMR) along with many previously under-resourced ones,
including implicit arguments and relations. The QAMR data and annotation code
is made publicly available to enable future work on how best to model these
complex phenomena.

本文介绍了问题 - 答案意义表示（QAMRs），并采用众包方案展示了 QAMRs 可以用非常少的训练进行标记，并收集了超过 5,000 个句子和 100,000 个问题的数据集。通过详细的定性分析，证明了众包生成的问题 - 答案对涵盖了现有数据集中绝大多数谓词 - 论元关系（包括 PropBank，NomBank，QA-SRL 和 AMR 等），以及许多先前资源匮乏的关系，包括隐含论元和关系。 QAMR 数据和注释代码公开提供，以便未来研究如何最好地对这些复杂现象进行建模。