论文标题
语言模型是否会对意大利照明零代词的核心代词做出类似人类的预测？
Do language models make human-like predictions about the coreferents of Italian anaphoric zero pronouns?
论文作者
论文摘要
某些语言允许在某些情况下省略参数。然而，人类语言理解者可靠地推断出这些零代词的预期参考人，部分原因是他们建立了对哪些参考人更有可能的期望。我们询问神经语言模型是否也提取了相同的期望。我们测试了12种当代语言模型是否显示出反映人类行为的期望，这些句子暴露于Carminati（2005）在意大利语中进行的五个行为实验中的零代词。我们发现三种模型-XGLM 2.9B，4.5B和7.5B-从所有实验中捕获人类行为，而其他实验则成功地对某些结果进行了建模。该结果表明，人类对核心的期望可以从接触语言中得出，并且还指示了语言模型的特征，使他们能够更好地反映人类的行为。
Some languages allow arguments to be omitted in certain contexts. Yet human language comprehenders reliably infer the intended referents of these zero pronouns, in part because they construct expectations about which referents are more likely. We ask whether Neural Language Models also extract the same expectations. We test whether 12 contemporary language models display expectations that reflect human behavior when exposed to sentences with zero pronouns from five behavioral experiments conducted in Italian by Carminati (2005). We find that three models - XGLM 2.9B, 4.5B, and 7.5B - capture the human behavior from all the experiments, with others successfully modeling some of the results. This result suggests that human expectations about coreference can be derived from exposure to language, and also indicates features of language models that allow them to better reflect human behavior.
