arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.09635cs.CL
收藏

细化语言模型的目标句法评估

Refining Targeted Syntactic Evaluation of Language Models

Stanford University(斯坦福大学)

Benjamin Newman, Kai-Siang Ang, Julia Gong, John Hewitt

摘要:

有针对性的英语主谓数一致性句法评估(TSE)使用手工制作的最小句子对来评估语言模型的句法知识,所述最小句子对仅在主要动词的变位上不同。该方法评估语言模型是否将每个语法句子评定为比其不语法对应物更可能。我们为TSE确定了两个不同的目标。首先,评估语言模型的句法知识的系统性:给定一个句子,它能正确地与任意动词共轭吗?第二,评估模型的可能行为:给定一个句子,模型是否将其概率质量集中在正确的动词上,即使只是在可能动词的子集上?我们认为,目前的实现TSE不直接捕获这些目标,并提出了新的指标来分别捕获每个目标。在我们的指标下,我们发现TSE高估了语言模型的系统性,但模型在预测上下文中可能出现的动词上的得分高出40%。

英文摘要:

Targeted syntactic evaluation of subject-verb number agreement in English (TSE) evaluates language models' syntactic knowledge using hand-crafted minimal pairs of sentences that differ only in the main verb's conjugation. The method evaluates whether language models rate each grammatical sentence as more likely than its ungrammatical counterpart. We identify two distinct goals for TSE. First, evaluating the systematicity of a language model's syntactic knowledge: given a sentence, can it conjugate arbitrary verbs correctly? Second, evaluating a model's likely behavior: given a sentence, does the model concentrate its probability mass on correctly conjugated verbs, even if only on a subset of the possible verbs? We argue that current implementations of TSE do not directly capture either of these goals, and propose new metrics to capture each goal separately. Under our metrics, we find that TSE overestimates systematicity of language models, but that models score up to 40% better on verbs that they predict are likely in context.

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。

↑