相关论文: Beyond English: Centering Multilingualism in Data …

Person re-identification is an important task that requires learning discriminative visual features for distinguishing different person identities. Diverse auxiliary information has been utilized to improve the visual feature learning. In…

Language provides a natural interface to specify and evaluate performance on visual tasks. To realize this possibility, vision language models (VLMs) must successfully integrate visual and linguistic information. Our work compares VLMs to a…

Multilingual representations pre-trained with monolingual data exhibit considerably unequal task performances across languages. Previous studies address this challenge with resource-intensive contextualized alignment, which assumes the…

Multi-modal machine translation aims at translating the source sentence into a different language in the presence of the paired image. Previous work suggests that additional visual information only provides dispensable help to translation,…

Learning word embeddings using distributional information is a task that has been studied by many researchers, and a lot of studies are reported in the literature. On the contrary, less studies were done for the case of multiple languages.…

Data Visualization has become an important aspect of big data analytics and has grown in sophistication and variety. We specifically identify the need for an analytical framework for data visualization with textual information. Data…

We present an analysis of the representation of gender as a data dimension in data visualizations and propose a set of considerations around visual variables and annotations for gender-related data. Gender is a common demographic dimension…

Multilingual programs, whose implementations are made of different languages, are gaining traction especially in domains, such as web programming, that particularly benefit from the additional flexibility brought by using multiple…

Emerging digital technologies are exacerbating the existing divide in Open Access Data (OAD) between high-and low-resource languages, excluding many communities from participating in the global digital transformation. In this PhD proposal,…

Humans use multiple senses to comprehend the environment. Vision and language are two of the most vital senses since they allow us to easily communicate our thoughts and perceive the world around us. There has been a lot of interest in…

While understanding and removing gender biases in language models has been a long-standing problem in Natural Language Processing, prior research work has primarily been limited to English. In this work, we investigate some of the…

Multilingual models have been widely used for cross-lingual transfer to low-resource languages. However, the performance on these languages is hindered by their underrepresentation in the pretraining data. To alleviate this problem, we…

The veracity of a factoid is largely independent of the language it is written in. However, language models are inconsistent in their ability to answer the same factual question across languages. This raises questions about how LLMs…

Cultural biases in multilingual datasets pose significant challenges for their effectiveness as global benchmarks. These biases stem not only from differences in language but also from the cultural knowledge required to interpret questions,…

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…

MIRACL (Multilingual Information Retrieval Across a Continuum of Languages) is a multilingual dataset we have built for the WSDM 2023 Cup challenge that focuses on ad hoc retrieval across 18 different languages, which collectively encompass…

Large Language Models (LLMs) are becoming increasingly capable across global languages. However, the ability to communicate across languages does not necessarily translate to appropriate cultural representations. A key concern is US-centric…

Despite recent advancements in vision-language models, their performance remains suboptimal on images from non-western cultures due to underrepresentation in training datasets. Various benchmarks have been proposed to test models' cultural…

Data literacy has become a key learning objective in K-12 education, but it remains an ambiguous concept as teachers interpret it differently. When creating assessments, teachers turn broad ideas about "working with data" into concrete…

Most multilingual question-answering benchmarks, while covering a diverse pool of languages, do not factor in regional diversity in the information they capture and tend to be Western-centric. This introduces a significant gap in fairly…