Because meaning can often be inferred from lexical semantics alone, word
order is often a redundant cue in natural language. For example, the words
chopped, chef, and onion are more likely used to convey "The chef chopped the
onion," not "The onion chopped the chef." Recent work has shown large language
models to be surprisingly word order invariant, but crucially has largely
considered natural prototypical inputs, where compositional meaning mostly
matches lexical expectations. To overcome this confound, we probe grammatical
role representation in English BERT and GPT-2, on instances where lexical
expectations are not sufficient, and word order knowledge is necessary for
correct classification. Such non-prototypical instances are naturally occurring
English sentences with inanimate subjects or animate objects, or sentences
where we systematically swap the arguments to make sentences like "The onion
chopped the chef". We find that, while early layer embeddings are largely
lexical, word order is in fact crucial in defining the later-layer
representations of words in semantically non-prototypical positions. Our
experiments isolate the effect of word order on the contextualization process,
and highlight how models use context in the uncommon, but critical, instances
where it matters.

通过探究自然语言处理模型中英语 BERT 和 GPT-2 语法角色的表示，发现其后期层次的单词聚类受到词序关系的影响，特别是在某些非典型语境下，词序知识对于正确的分类具有重要的作用，这突出了模型在非常规但至关重要的时刻如何使用上下文。