The advantage of starting big: Learning from unsegmented input facilitates mastery of grammatical gender in an artificial language

• We propose adults’ existing knowledge of words impacts how they learn a second language.
• Specifically, adults rely less on multiword units which harms learning certain aspects of language.
• We manipulate unit size during initial exposure in two artificial language studies.
• Learning from multiword units led to better learning of certain grammatical relations, but not others.
• We offer a novel account for L2 difficulty, relating unit size to specific learning outcomes.

Why is it difficult to learn a second language as an adult? We focus on the way adults’ existing knowledge of words impacts L2 learning. We suggest adults’ prior knowledge leads them to rely less on multiword units, and that this hinders learning certain grammatical relations between words. We test this prediction in two artificial language learning studies of grammatical gender with adult learners. In the first study, we manipulate whether the artificial language is segmented during initial learning and show that learning from unsegmented input leads to more article–noun units, and to better learning. Individually, learners who were more likely to treat the article and noun as one unit showed better learning on an off-line measure, confirming the link between unit-size and learning outcomes. In the second study, we show this pattern does not hold when the article conveys semantic information (animate vs. inanimate), illustrating the way unit size interacts with informativity during learning. The findings provide novel evidence for the advantage of learning grammar from multiword units, highlight the benefit of learning segmentation and structure simultaneously, and offer an experience-based explanation for L1–L2 differences that relates building blocks to learning outcomes.