Affixation patterns in native language and sequence processing by statistical learning mechanisms

Abstract

The suffixing bias (the tendency to exploit suffixes more often than prefixes to express grammatical meanings) in world's languages was identified a century ago, yet we still lack a clear account for why it emerged, namely, whether the bias emerged because general cognitive mechanisms shape languages to be more easily processed by available cognitive machinery, or the bias is speech-specific and is determined by domain-specific mechanisms. We used statistical learning (SL) experiments to compare processing of suffixed and prefixed sequences on linguistic and non-linguistic material. SL is not speech-specific, and we observed the suffixing preference only on linguistic material, suggesting its language-specific origin. Moreover, morphological properties of native languages (existence of grammatical prefixes) modulate suffixing preferences in SL experiments only on linguistic material, suggesting limited cross-domain transfer.

Keywords: Suffix Effect; morphological typology; serial recall; statistical learning; suffixing bias.

Graphical abstract

Figure 1.

Frames (rows) show the six possible combinations of words, affixes, and fillers. Each square represents a syllable: filled squares represent bi-syllabic stems; patterned squares represent affixes, with suffixes appended after and prefixes before the stem; unfilled squares are fillers (likely to be interpreted as prepositions or postpositions, depending on biases determined by listeners’ native languages). Auditory sequences include six frames, randomly concatenated such that each frame is used an equal number of times.

Figure 2.

The number of correct responses per group (Basque–Spanish bilinguals and Spanish monolinguals) and material type (linguistic and non-linguistic). The plot in the left column display means and 95% CI. The plot in the middle column displays probability density, individual datapoints, medians, and top and bottom quartiles as whiskers. The dotted line stands for the chance level (50% – 9 correct responses can be given by chance). The plot in the right column shows prior and posterior probabilities (with 95% credible interval) for the difference in the number of correct responses per sample and the average number of correct responses that could be expected by chance. The dots show prior and posterior density at the test value. The pie chart represents the estimated degree of support for the null (H0, unfilled part of the chart) and alternative (H1, filled part of the chart) hypotheses.

Figure 3.

Prior and posterior probabilities (with 95% credible interval) and strength of evidence for the alternative and the null hypotheses given the observed data. Left: Basque–Spanish bilinguals recognize prefixed sequences better than Spanish monolinguals (the alternative hypothesis is 4 times more likely than the null hypothesis – Basque bilinguals do not recognize prefixed sequences better than Spanish monolinguals). Right: Basque–Spanish bilinguals and Spanish monolinguals recognize suffixed sequences equally likely (the null hypothesis is 3.5 times more likely than the alternative hypothesis – there is difference in recognition rate of prefixed suffixes between the groups). The pie charts represent the estimated degree of support for the null (H0, unfilled part of the chart) and alternative (H1, filled part of the chart) hypotheses.

Figure 4.

(a) The percentage of prefixed sequences (preferred over suffixed sequences) on linguistic (left) and non-linguistic (right) material by Basque–Spanish bilinguals. The upper plots display probability density, individual datapoints, medians, top and bottom quartiles as whiskers. The bottom plots show prior and posterior probabilities (with 95% credible interval) for the difference in the number of selected prefixed sequences by participants and the number that could be expected by chance. The dots show prior and posterior density at the test value. The pie chart represents the estimated degree of support for the null (H0, unfilled part of the chart) and alternative (H1, filled part of the chart) hypotheses. (b) The percentage of prefixed sequences (preferred over suffixed sequences) on linguistic (left) and non-linguistic (right) material by Spanish monolinguals. The upper plots display probability density, individual datapoints, medians, top and bottom quartiles as whiskers. The bottom plots show prior and posterior probabilities (with 95% credible interval) for the difference in the number of selected prefixed sequences by participants and the number that could be expected by chance. The dots show prior and posterior density at the test value. The pie chart represents the estimated degree of support for the null (H0, unfilled part of the chart) and alternative (H1, filled part of the chart) hypotheses.