This paper describes the submission of Team “Giving it a Shot” to the AmericasNLP 2024 Shared Task on Creation of Educational Materials for Indigenous Languages. We use a simple few-shot prompting approach with several state of the art large language models, achieving competitive performance on the shared task, with our best system placing third overall. We perform a preliminary analysis to determine to what degree the performance of our model is due to prior exposure to the task languages, finding that generally our performance is better explained as being derived from in-context learning capabilities.

In morphology, a distinction is commonly drawn between inflection and derivation. However, a precise definition of this distinction which captures the way the terms are used across languages remains elusive within linguistic theory, typically being based on subjective tests. In this study, we present 4 quantitative measures which use the statistics of a raw text corpus in a language to estimate how much and how variably a morphological construction changes aspects of the lexical entry, specifically, the word’s form and the word’s semantic and syntactic properties (as operationalised by distributional word embeddings). Based on a sample of 26 languages, we find that we can reconstruct 90% of the classification of constructions into inflection and derivation in Unimorph using our 4 measures, providing large-scale cross-linguistic evidence that the concepts of inflection and derivation are associated with measurable signatures in terms of form and distribution signatures that behave consistently across a variety of languages. Critically, our measures and models are entirely language-agnostic, yet perform well across all languages studied. We find that while there is a high degree of consistency in the use of the terms inflection and derivation in terms of our measures, there are still many constructions near the model’s decision boundary between the two categories, indicating a gradient, rather than categorical, distinction.

In this paper, we present a straightforward technique for constructing interpretable word embeddings from morphologically analyzed examples (such as interlinear glosses) for all of the world’s languages. Currently, fewer than 300-400 languages out of approximately 7000 have have more than a trivial amount of digitized texts; of those, between 100-200 languages (most in the Indo-European language family) have enough text data for BERT embeddings of reasonable quality to be trained. The word embeddings in this paper are explicitly designed to be both linguistically interpretable and fully capable of handling the broad variety found in the world’s diverse set of 7000 languages, regardless of corpus size or morphological characteristics. We demonstrate the applicability of our representation through examples drawn from a typologically diverse set of languages whose morphology includes prefixes, suffixes, infixes, circumfixes, templatic morphemes, derivational morphemes, inflectional morphemes, and reduplication.

Machine translation has seen rapid progress with the advent of Transformer-based models. These models have no explicit linguistic structure built into them, yet they may still implicitly learn structured relationships by attending to relevant tokens. We hypothesize that this structural learning could be made more robust by explicitly endowing Transformers with a structural bias, and we investigate two methods for building in such a bias. One method, the TP-Transformer, augments the traditional Transformer architecture to include an additional component to represent structure. The second method imbues structure at the data level by segmenting the data with morphological tokenization. We test these methods on translating from English into morphologically rich languages, Turkish and Inuktitut, and consider both automatic metrics and human evaluations. We find that each of these two approaches allows the network to achieve better performance, but this improvement is dependent on the size of the dataset. In sum, structural encoding methods make Transformers more sample-efficient, enabling them to perform better from smaller amounts of data.

Prior studies in multilingual language modeling (e.g., Cotterell et al., 2018; Mielke et al., 2019) disagree on whether or not inflectional morphology makes languages harder to model. We attempt to resolve the disagreement and extend those studies. We compile a larger corpus of 145 Bible translations in 92 languages and a larger number of typological features.1 We fill in missing typological data for several languages and consider corpus-based measures of morphological complexity in addition to expert-produced typological features. We find that several morphological measures are significantly associated with higher surprisal when LSTM models are trained with BPE-segmented data. We also investigate linguistically motivated subword segmentation strategies like Morfessor and Finite-State Transducers (FSTs) and find that these segmentation strategies yield better performance and reduce the impact of a language’s morphology on language modeling.

Recently, large-scale pre-trained neural network models such as BERT have achieved many state-of-the-art results in natural language processing. Recent work has explored the linguistic capacities of these models. However, no work has focused on the ability of these models to generalize these capacities to novel words. This type of generalization is exhibited by humans, and is intimately related to morphology—humans are in many cases able to identify inflections of novel words in the appropriate context. This type of morphological capacity has not been previously tested in BERT models, and is important for morphologically-rich languages, which are under-studied in the literature regarding BERT’s linguistic capacities. In this work, we investigate this by considering monolingual and multilingual BERT models’ abilities to agree in number with novel plural words in English, French, German, Spanish, and Dutch. We find that many models are not able to reliably determine plurality of novel words, suggesting potential deficiencies in the morphological capacities of BERT models.

We present a novel method for embedding trees in a vector space based on Tensor-Product Representations (TPRs) which allows for inversion: the retrieval of the original tree structure and nodes from the vectorial embedding. Unlike previous attempts, this does not come at the cost of intractable representation size; we utilize a method for non-exact inversion, showing that it works well when there is sufficient randomness in the representation scheme for simple data and providing an upper bound on its error. To handle the huge number of possible tree positions without memoizing position representation vectors, we present a method (Cryptographic Role Embedding) using cryptographic hashing algorithms that allows for the representation of unboundedly many positions. Through experiments on parse tree data, we show a 30,000-dimensional Cryptographic Role Embedding of trees can provide invertibility with error < 1% that previous methods would require 8.6 × 1057 dimensions to represent.