According to the internationally recognized PIRLS (Progress in International Reading Literacy Study) assessment standards, reading comprehension questions should require not only information retrieval, but also higher-order processes such as inferencing, interpreting and evaluation. However, these kinds of questions are often not available in large quantities for training question generation models. This paper investigates whether pre-trained Large Language Models (LLMs) can produce higher-order questions. Human assessment on a Chinese dataset shows that few-shot LLM prompting generates more usable and higher-order questions than two competitive neural baselines.

Commonly found in academic and formal texts, a nominalization uses a deverbal noun to describe an event associated with its corresponding verb. Nominalizations can be difficult to interpret because of ambiguous semantic relations between the deverbal noun and its arguments. Automatic generation of clausal paraphrases for nominalizations can help disambiguate their meaning. However, previous work has not identified cases where it is awkward or impossible to paraphrase a compound nominalization. This paper investigates unsupervised prediction of paraphrasability, which determines whether the prenominal modifier of a nominalization can be re-written as a noun or adverb in a clausal paraphrase. We adopt the approach of overgenerating candidate paraphrases followed by candidate ranking with a neural language model. In experiments on an English dataset, we show that features from an Abstract Meaning Representation graph lead to statistically significant improvement in both paraphrasability prediction and paraphrase generation.