用左角递归神经网络文法建模人类句子加工
Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars
AI总结：
本文通过对比 LSTM 与采用自顶向下和左角解析策略的 RNNGs 在日语阅读时间上的表现，发现左角 RNNGs 最符合人类认知，证明层级加左角架构更具认知合理性。
摘要：
在计算语言学中，已有研究表明层级结构使语言模型（LMs）更接近人类。然而，以往文献对层级模型所采用的解析策略并未给出明确结论。本文考察了层级结构是否使语言模型更接近人类，以及如果是，哪种解析策略在认知上最合理。为回答这一问题，我们在日语中心语后置、左分支结构的条件下，将三个语言模型与人类阅读时间进行对比评估：作为序列模型的长短期记忆网络（LSTM），以及作为层级模型、分别采用自顶向下和左角解析策略的递归神经网络文法（RNNGs）。我们的计算建模表明，左角 RNNGs 优于自顶向下 RNNGs 和 LSTM，说明层级结构和左角架构在认知上比自顶向下或序列架构更合理。此外，本文还将讨论认知合理性与（i）困惑度、（ii）解析以及（iii）束搜索宽度之间的关系。
英文摘要：
In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like. However, the previous literature has been agnostic about a parsing strategy of the hierarchical models. In this paper, we investigated whether hierarchical structures make LMs more human-like, and if so, which parsing strategy is most cognitively plausible. In order to address this question, we evaluated three LMs against human reading times in Japanese with head-final left-branching structures: Long Short-Term Memory (LSTM) as a sequential model and Recurrent Neural Network Grammars (RNNGs) with top-down and left-corner parsing strategies as hierarchical models. Our computational modeling demonstrated that left-corner RNNGs outperformed top-down RNNGs and LSTM, suggesting that hierarchical and left-corner architectures are more cognitively plausible than top-down or sequential architectures. In addition, the relationships between the cognitive plausibility and (i) perplexity, (ii) parsing, and (iii) beam size will also be discussed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
