The success of neural language models (LMs) on many technological tasks has brought about their potential relevance as scientific theories of language despite some clear differences between LM training and child language acquisition. In this paper we argue that some of the most prominent benchmarks for evaluating the syntactic capacities of LMs may not be sufficiently rigorous. In particular, we show that the template-based benchmarks lack the structural diversity commonly found in the theoretical and psychological studies of language. When trained on small-scale data modeling child language acquisition, the LMs can be readily matched by simple baseline models. We advocate for the use of the readily available, carefully curated datasets that have been evaluated for gradient acceptability by large pools of native speakers and are designed to probe the structural basis of grammar specifically. On one such dataset, the LI-Adger dataset, LMs evaluate sentences in a way inconsistent with human language users. We conclude with suggestions for better connecting LMs with the empirical study of child language acquisition.

This paper describes a language-independent model for fully unsupervised morphological analysis that exploits a universal framework leveraging morphological typology. By modeling morphological processes including suffixation, prefixation, infixation, and full and partial reduplication with constrained stem change rules, our system effectively constrains the search space and offers a wide coverage in terms of morphological typology. The system is tested on nine typologically and genetically diverse languages, and shows superior performance over leading systems. We also investigate the effect of an oracle that provides only a handful of bits per language to signal morphological type.

Sentences are represented as hierarchical syntactic structures, which have been successfully modeled in sentence processing. In contrast, despite the theoretical agreement on hierarchical syntactic structures within words, words have been argued to be computationally less complex than sentences and implemented by finite-state models as linear strings of morphemes, and even the psychological reality of morphemes has been denied. In this paper, extending the computational models employed in sentence processing to morphological processing, we performed a computational simulation experiment where, given incremental surprisal as a linking hypothesis, five computational models with different representational assumptions were evaluated against human reaction times in visual lexical decision experiments available from the English Lexicon Project (ELP), a “shared task” in the morphological processing literature. The simulation experiment demonstrated that (i) “amorphous” models without morpheme units underperformed relative to “morphous” models, (ii) a computational model with hierarchical syntactic structures, Probabilistic Context-Free Grammar (PCFG), most accurately explained human reaction times, and (iii) this performance was achieved on top of surface frequency effects. These results strongly suggest that morphological processing tracks morphemes incrementally from left to right and parses them into hierarchical syntactic structures, contrary to “amorphous” and finite-state models of morphological processing.

This paper describes an unsupervised model for morphological segmentation that exploits the notion of paradigms, which are sets of morphological categories (e.g., suffixes) that can be applied to a homogeneous set of words (e.g., nouns or verbs). Our algorithm identifies statistically reliable paradigms from the morphological segmentation result of a probabilistic model, and chooses reliable suffixes from them. The new suffixes can be fed back iteratively to improve the accuracy of the probabilistic model. Finally, the unreliable paradigms are subjected to pruning to eliminate unreliable morphological relations between words. The paradigm-based algorithm significantly improves segmentation accuracy. Our method achieves start-of-the-art results on experiments using the Morpho-Challenge data, including English, Turkish, and Finnish.