相关论文: The mutual exclusivity bias of bilingual visually …

When children learn new words, they employ constraints such as the mutual exclusivity (ME) bias: a novel word is mapped to a novel object rather than a familiar one. This bias has been studied computationally, but only in models that use…

Strong inductive biases allow children to learn in fast and adaptable ways. Children use the mutual exclusivity (ME) bias to help disambiguate how words map to referents, assuming that if an object has one label then it does not need…

This paper introduces MEBench, a novel benchmark for evaluating mutual exclusivity (ME) bias, a cognitive phenomenon observed in children during word learning. Unlike traditional ME tasks, MEBench further incorporates spatial reasoning to…

This dissertation examines visually grounded speech (VGS) models that learn from unlabelled speech paired with images. It focuses on applications for low-resource languages and understanding human language acquisition. We introduce a task…

We present the first systematic evaluation of mutual exclusivity (ME) -- the bias to map novel words to novel referents -- in text-only language models trained on child-directed speech. We operationalise ME as referential suppression: when…

Children's tendency to associate novel words with novel referents has been taken to reflect a bias toward mutual exclusivity. This tendency may be advantageous both as (1) an ad-hoc referent selection heuristic to single out referents…

This paper introduces Low-shot Object Learning with Mutual Exclusivity Bias (LSME), the first computational framing of mutual exclusivity bias, a phenomenon commonly observed in infants during word learning. We provide a novel dataset,…

Multimodal VAEs seek to model the joint distribution over heterogeneous data (e.g.\ vision, language), whilst also capturing a shared representation across such modalities. Prior work has typically combined information from the modalities…

Language bias is a critical issue in Visual Question Answering (VQA), where models often exploit dataset biases for the final decision without considering the image information. As a result, they suffer from performance drop on…

Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space. Unsupervised MWE (UMWE) methods acquire multilingual embeddings without cross-lingual supervision, which is a significant…

Unlike most neural language models, humans learn language in a rich, multi-sensory and, often, multi-lingual environment. Current language models typically fail to fully capture the complexities of multilingual language use. We train an…

We investigate the behaviour of attention in neural models of visually grounded speech trained on two languages: English and Japanese. Experimental results show that attention focuses on nouns and this behaviour holds true for two very…

Visual grounding of Language aims at enriching textual representations of language with multiple sources of visual knowledge such as images and videos. Although visual grounding is an area of intense research, inter-lingual aspects of…

Visual commonsense understanding requires Vision Language (VL) models to not only understand image and text but also cross-reference in-between to fully integrate and achieve comprehension of the visual scene described. Recently, various…

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…

A desirable trait of an artificial agent acting in the visual world is to continually learn a sequence of language-informed tasks while striking a balance between sufficiently specializing in each task and building a generalized knowledge…

Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically…

Machine Interpreting systems are currently implemented as unimodal, real-time speech-to-speech architectures, processing translation exclusively on the basis of the linguistic signal. Such reliance on a single modality, however, constrains…

Unlike traditional vision-only models, vision language models (VLMs) offer an intuitive way to access visual content through language prompting by combining a large language model (LLM) with a vision encoder. However, both the LLM and the…

Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models…