This paper focuses on data-driven dependency parsing for Vedic Sanskrit. We propose and evaluate a transfer learning approach that benefits from syntactic analysis of typologically related languages, including Ancient Greek and Latin, and a descendant language - Classical Sanskrit. Experiments on the Vedic TreeBank demonstrate the effectiveness of cross-lingual transfer, demonstrating improvements from the biaffine baseline as well as outperforming the current state of the art benchmark, the deep contextualised self-training algorithm, across a wide range of experimental setups.

Despite the widespread use of English as a Second or Foreign Language (ESFL), developing syntactico-semantic representations for it is limited — the irregularities in ESFL complicate systematic composition and subsequently the derivation of its semantics.This paper draws on constructivism and proposes a novel Synchronous Hyperedge Replacement Grammar (SHRG)-based constructivist approach to address the challenges. By using constructions as fundamental units, this approach not only accommodates both the idiosyncrasies and the compositional nature of ESFL, but also bridges the gap between literal cues and intended meaning.The feasibility of this constructivist approach is demonstrated using real ESFL data, resulting in a gold-standard, medium-sized syntactico-semantic bank that covers a wide range of ESFL phenomena.

We introduce a computational framework for modeling child language production, focusing on the acquisition of the competence to map meaning onto linguistic form. Our approach uses graphs to formalize meaning and Synchronous Hyperedge Replacement Grammar (SHRG) to formalize the syntax–semantics interface.The setup provides computationally-sound induction algorithms of statistical grammar knowledge. We induce SHRGs solely from semantic graphs, and the resulting interpretable grammars are evaluated by their ability to generate utterances—providing a novel controlled paradigm to simulate child language acquisition.A notable finding is that unsupervised statistical learning (analogous to children’s implicit learning mechanisms) performs as well as the corresponding supervised oracle when a proper symbolic grammar is assumed (reflecting knowledge gained via comprehension).

We investigate the performance of state-of-the-art (SotA) neural grammar induction (GI) models on a morphemically tokenised English dataset based on the CHILDES treebank (Pearl and Sprouse, 2013). Using implementations from Yang et al. (2021a), we train models and evaluate them with the standard F1 score. We introduce novel evaluation metrics—depth-of-morpheme and sibling-of-morpheme—which measure phenomena around bound morpheme attachment. Our results reveal that models with the highest F1 scores do not necessarily induce linguistically plausible structures for bound morpheme attachment, highlighting a key challenge for cognitively plausible GI.

Cross-lingual extensions of the BabyLM Shared Task beyond English incentivise the development of Small Language Models that simulate a much wider range of language acquisition scenarios, including code-switching, simultaneous and successive bilingualism and second language acquisition. However, to our knowledge, there is no benchmark of the formal competence of cognitively-inspired models of L2 acquisition, or L2LMs. To address this, we introduce a Benchmark of Learner Interlingual Syntactic Structure (BLiSS). BLiSS consists of 1.5M naturalistic minimal pairs dataset derived from errorful sentence–correction pairs in parallel learner corpora. These are systematic patterns –overlooked by standard benchmarks of the formal competence of Language Models – which we use to evaluate L2LMs trained in a variety of training regimes on specific properties of L2 learner language to provide a linguistically-motivated framework for controlled measure of the interlanguage competence of L2LMs.