Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures

Research on the cognitive plausibility of language models (LMs) has so far mostly concentrated on modelling psycholinguistic response variables such as reading times, gaze durations and N400/P600 EEG signals, while mostly leaving out the dimension of what Mahowald et al. (2023) described as formal and functional linguistic competence, and developmental plausibility. We address this gap by training a series of GPT-like language models of different sizes on the strict version of the BabyLM pretraining corpus, evaluating on the challenge tasks (BLiMP, GLUE, MSGS) and an additional reading time prediction task. We find a positive correlation between LM size and performance on all three challenge tasks, with different preferences for model width and depth in each of the tasks. In contrast, a negative correlation was found between LM size and reading time fit of linear mixed-effects models using LM surprisal as a predictor, with the second-smallest LM achieving the largest log-likelihood reduction over a baseline model without surprisal. This suggests that modelling processing effort and linguistic competence may require an approach different from training GPT-like LMs on a developmentally plausible corpus.

A Lightweight Method to Generate Unanswerable Questions in English

If a question cannot be answered with the available information, robust systems for question answering (QA) should know _not_ to answer. One way to build QA models that do this is with additional training data comprised of unanswerable questions, created either by employing annotators or through automated methods for unanswerable question generation. To show that the model complexity of existing automated approaches is not justified, we examine a simpler data augmentation method for unanswerable question generation in English: performing antonym and entity swaps on answerable questions. Compared to the prior state-of-the-art, data generated with our training-free and lightweight strategy results in better models (+1.6 F1 points on SQuAD 2.0 data with BERT-large), and has higher human-judged relatedness and readability. We quantify the raw benefits of our approach compared to no augmentation across multiple encoder models, using different amounts of generated data, and also on TydiQA-MinSpan data (+9.3 F1 points with BERT-large). Our results establish swaps as a simple but strong baseline for future work.

Information-Theoretic Characterization of Vowel Harmony: A Cross-Linguistic Study on Word Lists

We present a cross-linguistic study that aims to quantify vowel harmony using data-driven computational modeling. Concretely, we define an information-theoretic measure of harmonicity based on the predictability of vowels in a natural language lexicon, which we estimate using phoneme-level language models (PLMs). Prior quantitative studies have relied heavily on inflected word-forms in the analysis of vowel harmony. We instead train our models using cross-linguistically comparable lemma forms with little or no inflection, which enables us to cover more under-studied languages. Training data for our PLMs consists of word lists with a maximum of 1000 entries per language. Despite the fact that the data we employ are substantially smaller than previously used corpora, our experiments demonstrate the neural PLMs capture vowel harmony patterns in a set of languages that exhibit this phenomenon. Our work also demonstrates that word lists are a valuable resource for typological research, and offers new possibilities for future studies on low-resource, under-studied languages.

On the N-gram Approximation of Pre-trained Language Models

Large pre-trained language models (PLMs) have shown remarkable performance across various natural language understanding (NLU) tasks, particularly in low-resource settings. Nevertheless, their potential in Automatic Speech Recognition (ASR) remains largely unexplored. This study investigates the potential usage of PLMs for language modelling in ASR. We compare the application of large-scale text sampling and probability conversion for approximating GPT-2 into an n-gram model. Furthermore, we introduce a vocabulary-restricted decoding method for random sampling, and evaluate the effects of domain difficulty and data size on the usability of generated text. Our findings across eight domain-specific corpora support the use of sampling-based approximation and show that interpolating with a large sampled corpus improves test perplexity over a baseline trigram by 15%. Our vocabulary-restricted decoding method pushes this improvement further by 5% in domain-specific settings.

An Information-Theoretic Analysis of Self-supervised Discrete Representations of Speech

Self-supervised representation learning for speech often involves a quantization step that transforms the acoustic input into discrete units. However, it remains unclear how to characterize the relationship between these discrete units and abstract phonetic categories such as phonemes. In this paper, we develop an information-theoretic framework whereby we represent each phonetic category as a distribution over discrete units. We then apply our framework to two different self-supervised models (namely wav2vec 2.0 and XLSR) and use American English speech as a case study. Our study demonstrates that the entropy of phonetic distributions reflects the variability of the underlying speech sounds, with phonetically similar sounds exhibiting similar distributions. While our study confirms the lack of direct, one-to-one correspondence, we find an intriguing, indirect relationship between phonetic categories and discrete units.

Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation

Few-shot fine-tuning and in-context learning are two alternative strategies for task adaptation of pre-trained language models. Recently, in-context learning has gained popularity over fine-tuning due to its simplicity and improved out-of-domain generalization, and because extensive evidence shows that fine-tuned models pick up on spurious correlations. Unfortunately, previous comparisons of the two approaches were done using models of different sizes. This raises the question of whether the observed weaker out-of-domain generalization of fine-tuned models is an inherent property of fine-tuning or a limitation of the experimental setup. In this paper, we compare the generalization of few-shot fine-tuning and in-context learning to challenge datasets, while controlling for the models used, the number of examples, and the number of parameters, ranging from 125M to 30B. Our results show that fine-tuned language models can in fact generalize well out-of-domain. We find that both approaches generalize similarly; they exhibit large variation and depend on properties such as model size and the number of examples, highlighting that robust task adaptation remains a challenge.

Weaker Than You Think: A Critical Look atWeakly Supervised Learning

Weakly supervised learning is a popular approach for training machine learning models in low-resource settings. Instead of requesting high-quality yet costly human annotations, it allows training models with noisy annotations obtained from various weak sources. Recently, many sophisticated approaches have been proposed for robust training under label noise, reporting impressive results. In this paper, we revisit the setup of these approaches and find that the benefits brought by these approaches are significantly overestimated. Specifically, we find that the success of existing weakly supervised learning approaches heavily relies on the availability of clean validation samples which, as we show, can be leveraged much more efficiently by simply training on them. After using these clean labels in training, the advantages of using these sophisticated approaches are mostly wiped out. This remains true even when reducing the size of the available clean data to just five samples per class, making these approaches impractical. To understand the true value of weakly supervised learning, we thoroughly analyse diverse NLP datasets and tasks to ascertain when and why weakly supervised approaches work, and provide recommendations for future research.

MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages

In this paper, we present MasakhaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss the challenges in annotating POS for these languages using the UD (universal dependencies) guidelines. We conducted extensive POS baseline experiments using conditional random field and several multilingual pre-trained language models. We applied various cross-lingual transfer models trained with data available in UD. Evaluating on the MasakhaPOS dataset, we show that choosing the best transfer language(s) in both single-source and multi-source setups greatly improves the POS tagging performance of the target languages, in particular when combined with cross-lingual parameter-efficient fine-tuning methods. Crucially, transferring knowledge from a language that matches the language family and morphosyntactic properties seems more effective for POS tagging in unseen languages.

$\varepsilon$ KÚ <MASK>: Integrating Yorùbá cultural greetings into machine translation

This paper investigates the performance of massively multilingual neural machine translation (NMT) systems in translating Yor\`ub\'a greetings ($\varepsilon$ k\'u [MASK]), which are a big part of Yor\`ub\'a language and culture, into English. To evaluate these models, we present IkiniYor\`ub\'a, a Yor\`ub\'a-English translation dataset containing some Yor\`ub\'a greetings, and sample use cases. We analysed the performance of different multilingual NMT systems including Google and NLLB and show that these models struggle to accurately translate Yor\`ub\'a greetings into English. In addition, we trained a Yor\`ub\'a-English model by finetuning an existing NMT model on the training split of IkiniYor\`ub\'a and this achieved better performance when compared to the pre-trained multilingual NMT models, although they were trained on a large volume of data.

Analyzing the Representational Geometry of Acoustic Word Embeddings

Acoustic word embeddings (AWEs) are vector representations such that different acoustic exemplars of the same word are projected nearby in the embedding space. In addition to their use in speech technology applications such as spoken term discovery and keyword spotting, AWE models have been adopted as models of spoken-word processing in several cognitively motivated studies and have been shown to exhibit human-like performance in some auditory processing tasks. Nevertheless, the representational geometry of AWEs remains an under-explored topic that has not been studied in the literature. In this paper, we take a closer analytical look at AWEs learned from English speech and study how the choice of the learning objective and the architecture shapes their representational profile. To this end, we employ a set of analytic techniques from machine learning and neuroscience in three different analyses: embedding space uniformity, word discriminability, and representational consistency. Our main findings highlight the prominent role of the learning objective on shaping the representation profile compared to the model architecture.