Related papers: Beyond English: Centering Multilingualism in Data …
English is the predominant language on the web, powering nearly half of the world's top ten million websites. Support for multilingual content is nevertheless growing, with many websites increasingly combining English with regional or…
Information Visualization techniques are built on a context with many factors related to both vision and cognition, making it difficult to draw a clear picture of how data visually turns into comprehension. In the intent of promoting a…
We explore the integration of large language models (LLMs) into visual analytics (VA) systems to transform their capabilities through intuitive natural language interactions. We survey current research directions in this emerging field,…
Data visualizations are ubiquitous in all disciplines and have become the primary means of analysing data and communicating insights. However, the predominant reliance on visual encoding of data continues to create accessibility barriers…
Does language help make sense of the visual world? How important is it to actually see the world rather than having it described with words? These basic questions about the nature of intelligence have been difficult to answer because we…
In this paper, we explore the learning of neural network embeddings for natural images and speech waveforms describing the content of those images. These embeddings are learned directly from the waveforms without the use of linguistic…
This paper discusses problems of visualizing humanities data of various forms, such as video data, archival data, and numeric-oriented social science data, with three distinct case studies. By describing the visualization practices and the…
In multilingual societies, social conversations often involve code-mixed speech. The current speech technology may not be well equipped to extract information from multi-lingual multi-speaker conversations. The DISPLACE challenge entails a…
Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few…
Large vision-language models (VLMs) can assist visually impaired people by describing images from their daily lives. Current evaluation datasets may not reflect diverse cultural user backgrounds or the situational context of this use case.…
Natural language and visualization are two complementary modalities of human communication that play a crucial role in conveying information effectively. While visualizations help people discover trends, patterns, and anomalies in data,…
Developments in data visualization research have enabled visualization systems to achieve great general usability and application across a variety of domains. These advancements have improved not only people's understanding of data, but…
Research has shown that while large language models (LLMs) can generate their responses based on cultural context, they are not perfect and tend to generalize across cultures. However, when evaluating the cultural bias of a language…
Bilingual and multilingual language models offer a promising path toward scaling NLP systems across diverse languages and users. However, their performance often varies wildly between languages as prior works show that adding more languages…
We report on a systematic, PRISMA-guided survey of research at the intersection of LLMs and visualization, with a particular focus on visio-verbal interaction -- where verbal and visual modalities converge to support data sense-making. The…
Despite significant advances in vision-language models (VLMs), most existing work follows an English-centric design process, limiting their effectiveness in multilingual settings. In this work, we provide a comprehensive empirical study…
This position paper discusses the problem of multilingual evaluation. Using simple statistics, such as average language performance, might inject linguistic biases in favor of dominant language families into evaluation methodology. We argue…
Large language models (LLMs) have demonstrated significant capabilities in solving mathematical problems expressed in natural language. However, multilingual and culturally-grounded mathematical reasoning in low-resource languages lags…
Multilingual alignment of sentence representations has mostly required bitexts to bridge the gap between languages. We investigate whether visual information can bridge this gap instead. Image caption datasets are very easy to create…
Anthropographics are human-shaped visualizations that have primarily been used within visualization research and data journalism to show humanitarian and demographic data. However, anthropographics have typically been produced by a small…