Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks.Yet, the exact capabilities of these black-box models are still poorly understood. While much of previous work has focused on studying their ability to learn meaning at the word-level, their ability to track syntactic dependencies between words has received less attention.We take a first step in closing this gap by creating a new multimodal task targeted at evaluating understanding of predicate-noun dependencies in a controlled setup.We evaluate a range of state-of-the-art models and find that their performance on the task varies considerably, with some models performing relatively well and others at chance level. In an effort to explain this variability, our analyses indicate that the quality (and not only sheer quantity) of pretraining data is essential. Additionally, the best performing models leverage fine-grained multimodal pretraining objectives in addition to the standard image-text matching objectives.This study highlights that targeted and controlled evaluations are a crucial step for a precise and rigorous test of the multimodal knowledge of vision-and-language models.

Children learn the meaning of words and sentences in their native language at an impressive speed and from highly ambiguous input. To account for this learning, previous computational modeling has focused mainly on the study of perception-based mechanisms like cross-situational learning. However, children do not learn only by exposure to the input. As soon as they start to talk, they practice their knowledge in social interactions and they receive feedback from their caregivers. In this work, we propose a model integrating both perception- and production-based learning using artificial neural networks which we train on a large corpus of crowd-sourced images with corresponding descriptions. We found that production-based learning improves performance above and beyond perception-based learning across a wide range of semantic tasks including both word- and sentence-level semantics. In addition, we documented a synergy between these two mechanisms, where their alternation allows the model to converge on more balanced semantic knowledge. The broader impact of this work is to highlight the importance of modeling language learning in the context of social interactions where children are not only understood as passively absorbing the input, but also as actively participating in the construction of their linguistic knowledge.

In this paper we describe our contribution to the CMCL 2021 Shared Task, which consists in predicting 5 different eye tracking variables from English tokenized text. Our approach is based on a neural network that combines both raw textual features we extracted from the text and parser-based features that include linguistic predictions (e.g. part of speech) and complexity metrics (e.g., entropy of parsing). We found that both the features we considered as well as the architecture of the neural model that combined these features played a role in the overall performance. Our system achieved relatively high accuracy on the test data of the challenge and was ranked 2nd out of 13 competing teams and a total of 30 submissions.

When learning their native language, children acquire the meanings of words and sentences from highly ambiguous input without much explicit supervision. One possible learning mechanism is cross-situational learning, which has been successfully tested in laboratory experiments with children. Here we use Artificial Neural Networks to test if this mechanism scales up to more natural language and visual scenes using a large dataset of crowd-sourced images with corresponding descriptions. We evaluate learning using a series of tasks inspired by methods commonly used in laboratory studies of language acquisition. We show that the model acquires rich semantic knowledge both at the word- and sentence-level, mirroring the patterns and trajectory of learning in early childhood. Our work highlights the usefulness of low-level co-occurrence statistics across modalities in facilitating the early acquisition of higher-level semantic knowledge.

The free association task has been very influential both in cognitive science and in computational linguistics. However, little research has been done to study how free associations develop in childhood. The current work focuses on the developmental hypothesis according to which free word associations emerge by mirroring the co-occurrence distribution of children’s linguistic environment. I trained a distributional semantic model on a large corpus of child language and I tested if it could predict children’s responses. The results largely supported the hypothesis: Co-occurrence-based similarity was a strong predictor of children’s associative behavior even controlling for other possible predictors such as phonological similarity, word frequency, and word length. I discuss the findings in the light of theories of conceptual development.

Interactive alignment is a major mechanism of linguistic coordination. Here we study the way this mechanism emerges in development across the lexical, syntactic, and conceptual levels. We leverage NLP tools to analyze a large-scale corpus of child-adult conversations between 2 and 5 years old. We found that, across development, children align consistently to adults above chance and that adults align consistently more to children than vice versa (even controlling for language production abilities). Besides these consistencies, we found a diversity of developmental trajectories across linguistic levels. These corpus-based findings provide strong support for an early onset of multi-level linguistic alignment in children and invites new experimental work.

How do children learn abstract concepts such as animal vs. artifact? Previous research has suggested that such concepts can partly be derived using cues from the language children hear around them. Following this suggestion, we propose a model where we represent the children’ developing lexicon as an evolving network. The nodes of this network are based on vocabulary knowledge as reported by parents, and the edges between pairs of nodes are based on the probability of their co-occurrence in a corpus of child-directed speech. We found that several abstract categories can be identified as the dense regions in such networks. In addition, our simulations suggest that these categories develop simultaneously, rather than sequentially, thanks to the children’s word learning trajectory which favors the exploration of the global conceptual space.