The P600 – not the N400 – indexes semantic integration

The N400 and P600 are the two most salient language-sensitive components of the Event-Related Potential (ERP) signal. Yet, their functional interpretation is still a matter of debate. Traditionally, the N400 is taken to reflect processes of semantic integration while the P600 is linked to structural reanalysis [1,2]. These views have, however, been challenged by so-called Semantic Illusions (SIs), where semantically anomalous target words produce P600-rather than N400-effects (e.g., “For breakfast the eggs/boys would eat”, [3]). To account for these findings, complex multi-stream models of language processing have been proposed in an attempt to maintain the traditional views on the N400 and the P600 (see [4] for a review). However, these models fail to account for SIs in wider discourse [5] and/or in absence of semantic violations [6]. In contrast, the Retrieval-Integration (RI) account [4] puts forward an explanation for elicitation pattern of the N400 and the P600 by rethinking their functional interpretations. According to the RI account, N400 amplitude reflects retrieval of lexical-semantic information form long-term memory, and is therefore sensitive to priming (in line with [7,8]), while processes of semantic integration are indexed by the P600. To provide decisive evidence for the P600/Integration hypothesis, we conducted an ERP study in which twenty-one participants read short discourses in which a non-anomalous target word (“menu”) was easy (a. John entered the restaurant. Before long he opened the menu and […]) vs. difficult (b. John left the restaurant. Before long he opened the menu and […]) to integrate into the unfolding discourse representation, but, crucially, was equally primed by the two contexts (through the word “restaurant”). The reduced plausibility of (b) compared to (a) was confirmed by offline plausibility ratings. Here, traditional accounts predict that difficulty in integrating the target word in (b) should elicit an N400-effect, and no P600-effect. By contrast, the RI account predicts no N400-effect (due to similar priming), but a P600-effect indexing semantic integration difficulty. As predicted by RI, we observed a larger P600 for (b) relative to (a), and no difference in N400 amplitude. Importantly, an N400-effect was observed for a further control condition in which the target word “menu” was not primed by the context (e.g., “John entered the apartment”), which elicited an increased N400 amplitude relative to (a) and (b). Taken together, our results provide clear evidence for the RI account: semantic integration is indexed by the P600 component, while the N400 is predominantly driven by priming. Our findings highlight the importance of establishing specific linking hypotheses to the N400 and P600 components in order to properly interpret ERP results for the development of more informed neurobiological models of language. [1] Brown & Hagoort (1993), JCN; [2] Osterhout & Holcomb (1992), JML; [3] Kuperberg et al. (2003), Brain Res Cogn Brain Res.; [4] Brouwer et al. (2012), Brain Res.; [5] Nieuwland & Van Berkum (2005), Cogn. Brain Res.; [6] Chow & Phillips (2013), Brain Res.; [7] Kutas & Federmeier (2000), TiCS; [8] Lau et al. (2008), Nat. Rev. Neurosci.