arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.04887cs.CL
收藏

神经语言模型中语篇结构与指称而非句法相互作用

Discourse structure interacts with reference but not syntax in neural language models

Cornell University(康奈尔大学)

Forrest Davis, Marten van Schijndel

摘要:

在大量文本上训练的语言模型(LM)被认为可以获得抽象的语言表示。我们的工作测试的鲁棒性,这些抽象的LMs学习不同的语言表示之间的相互作用的能力。特别是,我们利用刺激心理语言学研究表明,人类可以条件参考(即共指消解)和句法处理相同的话语结构(隐含的因果关系)。我们比较了Transformer和长短期记忆LM,发现与人类相反,尽管模型表征编码了必要的话语信息,但隐式因果关系仅影响LM行为以供参考,而不是句法。我们的研究结果进一步表明,LM的行为可以矛盾,不仅学到的话语表示,但也句法协议,指出标准的语言建模的缺点。

英文摘要:

Language models (LMs) trained on large quantities of text have been claimed to acquire abstract linguistic representations. Our work tests the robustness of these abstractions by focusing on the ability of LMs to learn interactions between different linguistic representations. In particular, we utilized stimuli from psycholinguistic studies showing that humans can condition reference (i.e. coreference resolution) and syntactic processing on the same discourse structure (implicit causality). We compared both transformer and long short-term memory LMs to find that, contrary to humans, implicit causality only influences LM behavior for reference, not syntax, despite model representations that encode the necessary discourse information. Our results further suggest that LM behavior can contradict not only learned representations of discourse but also syntactic agreement, pointing to shortcomings of standard language modeling.

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。

↑