@article{jbp:/content/journals/10.1075/ml.6.2.04tre, author = "Tremblay, Antoine and Tucker, Benjamin V.", title = "The effects of N-gram probabilistic measures on the recognition and production of four-word sequences", journal= "The Mental Lexicon", year = "2011", volume = "6", number = "2", pages = "302-324", doi = "https://doi.org/10.1075/ml.6.2.04tre", url = "https://www.jbe-platform.com/content/journals/10.1075/ml.6.2.04tre", publisher = "John Benjamins", issn = "1871-1340", type = "Journal Article", keywords = "frequency of occurrence", keywords = "N-grams", keywords = "speech processing", keywords = "multi-word sequences", keywords = "mutual information", keywords = "log probability of occurrence", keywords = "mixed-effects regression", keywords = "speech production", keywords = "logit", abstract = "The present study investigates the processing and production of four-word sequences such as I don’t really know, at the age of, and I think it’s the. Specifically, we investigate the influence of families of probabilistic measures such as unigram, bigram, trigram, and quadgram frequency of occurrence, logarithmic (log) probability of occurrence, and mutual information. Log probability of occurrence emerged as the predominant predictor family in the onset latency analysis, suggesting that recognition is mainly underpinned by competition between a target N-gram and its family members. In contrast, the amount of experience one has with an N-gram (frequency of occurrence) surfaced as the most prominent predictor in production. Further, probabilistic measures tied to trigrams surfaced as the best predictors in the onset latency analysis, while the measures tied to unigrams were most predictive of production durations.Finally, the interactions between probabilistic measures tied to unigrams, bigrams, trigrams, and quadgrams suggest that N-grams of different lengths are processed in parallel in both recognition and production.", }