Semantics drives analogical change in Germanic strong verb paradigms: a phylogenetic study

TL;DR

The problem is to explain cross-language persistence of irregular stem alternations in Germanic strong verbs, particularly the $ABB$ pattern, given semantic changes in present-perfect usage. The authors apply a hierarchical phylogenetic continuous-time Markov model (CTM) to 107 cognate verbs across 14 Germanic languages, contrasting regimes where present perfect is extended to narrative past ($E$) vs. non-extended ($N$). They find higher stationary probability of $ABB$ and lower for $AAA$ in the extended regime, with $ABB$ exit rates reduced and hierarchical pooling improving predictive fit (ELPD difference = $57.90$, SE = $11.87$). The results support a conservation-based account of irregular morphology and demonstrate a scalable phylogenetic approach for assessing semantic-morphology interactions.

Abstract

A large body of research on morphological paradigms makes the prediction that irregular morphological patterns of allomorphy are more likely to emerge and persist when they serve to mark important functional distinctions. More specifically, it has been observed that in some Germanic languages in which narrative past tense is expressed by the past participle, there is a greater affinity for stem allomorphy shared by preterite forms and past participles to the exclusion of present forms (the so-called ABB pattern), as it serves to enhance marking of the binary semantic opposition between present and past. Using data from 107 cognate verbs attested across 14 archaic and contemporary Germanic languages and a novel hierarchical phylogenetic model, we show that there is a greater long-term preference for this alternation pattern in situations where narrative past tense has been extended to the past participle, confirming this hypothesis. We further elucidate the mechanisms underlying this association, demonstrating that this association holds because verbs with the ABB pattern are more likely to preserve it in situations where it marks an important binary semantic opposition; however, there is less evidence that the ABB pattern is extended to verbs with different patterns under the same circumstances. These results bear on debate as to whether the distribution of irregularity we observe cross-linguistically is due primarily to (1) the preservation of irregular patterns or (2) an active drive toward irregularization in certain contexts, and are more in line with the first hypothesis.

Figures (10)

• Figure 1: (a) dammel_etal2010 propose an explanation according to which the greater functional expansion of perfect leads to leveling in the stem vowel of the past participle; (b) desmet_vandevelde2019, on the other hand, conclude that situations such as the one in Stage 2 and 4, where past tense and perfect overlap in their function, lead to a greater preference for partial leveling, with the past tense and past participle having the same stem vowel and the infinitive having a different one.
• Figure 2: The distribution of classes (cf. mhg_dict) for the 107 verbs in the dataset. For classes 5, 6 and 7, both strong verbs and *j-present strong verbs are counted. For class 7, all subclasses (e.g., 7a) are included in the count.
• Figure 3: The distribution of missing verbs per language, out of a total of 107.
• Figure 4: The distribution of coded vowel alternation patterns for each language.
• Figure 5: A sample of verbs and their coded patterns mapped to a Maximum Clade Credibility tree from chang2015.