Search

Automatically generating data visualizations in response to human utterances on datasets necessitates a deep semantic understanding of the data utterance, including implicit and explicit references to data attributes, visualization tasks, and necessary data preparation steps. Natural Language Interfaces (NLIs) for data visualization have explored ways to infer such information, yet challenges persist due to inherent uncertainty in human speech. Recent advances in Large Language Models (LLMs) provide an avenue to address these challenges, but their ability to extract the relevant semantic information remains unexplored. In this study, we evaluate four publicly available LLMs (GPT-4, Gemini-Pro, Llama3, and Mixtral), investigating their ability to comprehend utterances even in the presence of uncertainty and identify the relevant data context and visual tasks. Our findings reveal that LLMs are sensitive to uncertainties in utterances. Despite this sensitivity, they are able to extract the relevant data context. However, LLMs struggle with inferring visualization tasks. Based on these results, we highlight future research directions on using LLMs for visualization generation., Comment: 5 pages, 4 figures, IEEE VIS short papers

The Sustainable Development Goals (SDGs) aim to resolve societal challenges, such as eradicating poverty and improving the lives of vulnerable populations in impoverished areas. Those areas rely on road infrastructure construction to promote accessibility and economic development. Although publicly available data like OpenStreetMap is available to monitor road status, data completeness in impoverished areas is limited. Meanwhile, the development of deep learning techniques and satellite imagery shows excellent potential for earth monitoring. To tackle the challenge of road network assessment in impoverished areas, we develop a systematic road extraction framework combining an encoder-decoder architecture and morphological operations on satellite imagery, offering an integrated workflow for interdisciplinary researchers. Extensive experiments of road network extraction on real-world data in impoverished regions achieve a 42.7% enhancement in the F1-score over the baseline methods and reconstruct about 80% of the actual roads. We also propose a comprehensive road network dataset covering approximately 794,178 km2 area and 17.048 million people in 382 impoverished counties in China. The generated dataset is further utilized to conduct socioeconomic analysis in impoverished counties, showing that road network construction positively impacts regional economic development. The technical appendix, code, and generated dataset can be found at https://github.com/tsinghua-fib-lab/Road_network_extraction_impoverished_counties., Comment: 12 pages, 13 figures, IJCAI2024 (AI and Social Good)

Large Language Models (LLMs) have demonstrated remarkable abilities in general scenarios. Instruction finetuning empowers them to align with humans in various tasks. Nevertheless, the Diversity and Quality of the instruction data remain two main challenges for instruction finetuning. With regard to this, in this paper, we propose a novel gradient-based method to automatically select high-quality and diverse instruction finetuning data for machine translation. Our key innovation centers around analyzing how individual training examples influence the model during training. Specifically, we select training examples that exert beneficial influences on the model as high-quality ones by means of Influence Function plus a small high-quality seed dataset. Moreover, to enhance the diversity of the training data we maximize the variety of influences they have on the model by clustering on their gradients and resampling. Extensive experiments on WMT22 and FLORES translation tasks demonstrate the superiority of our methods, and in-depth analysis further validates their effectiveness and generalization., Comment: Accepted to ACL 2024 main conference

Content creation today often takes place via collaborative writing. A longstanding interest of CSCW research lies in understanding and promoting the coordination between co-writers. However, little attention has been paid to individuals who write in their non-native language and to co-writer groups involving them. We present a mixed-method study that fills the above gap. Our participants included 32 co-writer groups, each consisting of one native speaker (NS) of English and one non-native speaker (NNS) with limited proficiency. They performed collaborative writing adopting two different workflows: half of the groups began with NNSs taking the first editing turn and half had NNSs act after NSs. Our data revealed a "late-mover disadvantage" exclusively experienced by NNSs: an NNS's ideational contributions to the joint document were suppressed when their editing turn was placed after an NS's turn, as opposed to ahead of it. Surprisingly, editing help provided by AI-powered tools did not exempt NNSs from being disadvantaged. Instead, it triggered NSs' overestimation of NNSs' English proficiency and agency displayed in the writing, introducing unintended tensions into the collaboration. These findings shed light on the fair assessment and effective promotion of a co-writer's contributions in language diverse settings. In particular, they underscore the necessity of disentangling contributions made to the ideational, expressional, and lexical aspects of the joint writing.

In this paper, we establish the second-order randomized identification capacity (RID capacity) of the Additive White Gaussian Noise Channel (AWGNC). On the one hand, we obtain a refined version of Hayashi's theorem to prove the achievability part. On the other, we investigate the relationship between identification and channel resolvability, then we propose a finer quantization method to prove the converse part. Consequently, the second-order RID capacity of the AWGNC has the same form as the second-order transmission capacity. The only difference is that the maximum number of messages in RID scales double exponentially in the blocklength., Comment: 7 pages, 3 figures, 1 table. This paper has been accepted by IEEE ISIT 2024. In response to the reviewer's feedback, we have incorporated additional references and refined the content in the introduction section and we replace some figures as the pdf form

Non-native English speakers (NNES) face challenges in digital workspace communication (e.g., emails, Slack messages), often inadvertently translating expressions from their native languages, which can lead to awkward or incorrect usage. Current AI-assisted writing tools are equipped with fluency enhancement and rewriting suggestions; however, NNES may struggle to grasp the subtleties among various expressions, making it challenging to choose the one that accurately reflects their intent. Such challenges are exacerbated in high-stake text-based communications, where the absence of non-verbal cues heightens the risk of misinterpretation. By leveraging the latest advancements in large language models (LLM) and word embeddings, we propose WordDecipher, an explainable AI-assisted writing tool to enhance digital workspace communication for NNES. WordDecipher not only identifies the perceived social intentions detected in users' writing, but also generates rewriting suggestions aligned with users' intended messages, either numerically or by inferring from users' writing in their native language. Then, WordDecipher provides an overview of nuances to help NNES make selections. Through a usage scenario, we demonstrate how WordDecipher can significantly enhance an NNES's ability to communicate her request, showcasing its potential to transform workspace communication for NNES., Comment: The Third Workshop on Intelligent and Interactive Writing Assistants (In2Writing) at CHI 2024

Generative image models have emerged as a promising technology to produce realistic images. Despite potential benefits, concerns grow about its misuse, particularly in generating deceptive images that could raise significant ethical, legal, and societal issues. Consequently, there is growing demand to empower users to effectively discern and comprehend patterns of AI-generated images. To this end, we developed ASAP, an interactive visualization system that automatically extracts distinct patterns of AI-generated images and allows users to interactively explore them via various views. To uncover fake patterns, ASAP introduces a novel image encoder, adapted from CLIP, which transforms images into compact "distilled" representations, enriched with information for differentiating authentic and fake images. These representations generate gradients that propagate back to the attention maps of CLIP's transformer block. This process quantifies the relative importance of each pixel to image authenticity or fakeness, exposing key deceptive patterns. ASAP enables the at scale interactive analysis of these patterns through multiple, coordinated visualizations. This includes a representation overview with innovative cell glyphs to aid in the exploration and qualitative evaluation of fake patterns across a vast array of images, as well as a pattern view that displays authenticity-indicating patterns in images and quantifies their impact. ASAP supports the analysis of cutting-edge generative models with the latest architectures, including GAN-based models like proGAN and diffusion models like the latent diffusion model. We demonstrate ASAP's usefulness through two usage scenarios using multiple fake image detection benchmark datasets, revealing its ability to identify and understand hidden patterns in AI-generated images, especially in detecting fake human faces produced by diffusion-based techniques., Comment: 9 pages, 6 figures

In an effort to reduce the computational load of Transformers, research on linear attention has gained significant momentum. However, the improvement strategies for attention mechanisms typically necessitate extensive retraining, which is impractical for large language models with a vast array of parameters. In this paper, we present DiJiang, a novel Frequency Domain Kernelization approach that enables the transformation of a pre-trained vanilla Transformer into a linear complexity model with little training costs. By employing a weighted Quasi-Monte Carlo method for sampling, the proposed approach theoretically offers superior approximation efficiency. To further reduce the training computational complexity, our kernelization is based on Discrete Cosine Transform (DCT) operations. Extensive experiments demonstrate that the proposed method achieves comparable performance to the original Transformer, but with significantly reduced training costs and much faster inference speeds. Our DiJiang-7B achieves comparable performance with LLaMA2-7B on various benchmark while requires only about 1/50 training cost. Code is available at https://github.com/YuchuanTian/DiJiang.

Mixed-media tutorials, which integrate videos, images, text, and diagrams to teach procedural skills, offer more browsable alternatives than timeline-based videos. However, manually creating such tutorials is tedious, and existing automated solutions are often restricted to a particular domain. While AI models hold promise, it is unclear how to effectively harness their powers, given the multi-modal data involved and the vast landscape of models. We present TutoAI, a cross-domain framework for AI-assisted mixed-media tutorial creation on physical tasks. First, we distill common tutorial components by surveying existing work; then, we present an approach to identify, assemble, and evaluate AI models for component extraction; finally, we propose guidelines for designing user interfaces (UI) that support tutorial creation based on AI-generated components. We show that TutoAI has achieved higher or similar quality compared to a baseline model in preliminary user studies., Comment: CHI 2024, supplementary materials: https://hdi.cs.umd.edu/papers/TutoAI_CHI24_Supp.pdf

Large Language Models (LLMs) can play a vital role in psychotherapy by adeptly handling the crucial task of cognitive reframing and overcoming challenges such as shame, distrust, therapist skill variability, and resource scarcity. Previous LLMs in cognitive reframing mainly converted negative emotions to positive ones, but these approaches have limited efficacy, often not promoting clients' self-discovery of alternative perspectives. In this paper, we unveil the Helping and Empowering through Adaptive Language in Mental Enhancement (HealMe) model. This novel cognitive reframing therapy method effectively addresses deep-rooted negative thoughts and fosters rational, balanced perspectives. Diverging from traditional LLM methods, HealMe employs empathetic dialogue based on psychotherapeutic frameworks. It systematically guides clients through distinguishing circumstances from feelings, brainstorming alternative viewpoints, and developing empathetic, actionable suggestions. Moreover, we adopt the first comprehensive and expertly crafted psychological evaluation metrics, specifically designed to rigorously assess the performance of cognitive reframing, in both AI-simulated dialogues and real-world therapeutic conversations. Experimental results show that our model outperforms others in terms of empathy, guidance, and logical coherence, demonstrating its effectiveness and potential positive impact on psychotherapy., Comment: 17 pages, 4 figures

The recent trend of large language models (LLMs) is to increase the scale of both model size (\aka the number of parameters) and dataset to achieve better generative ability, which is definitely proved by a lot of work such as the famous GPT and Llama. However, large models often involve massive computational costs, and practical applications cannot afford such high prices. However, the method of constructing a strong model architecture for LLMs is rarely discussed. We first analyze the state-of-the-art language model architectures and observe the feature collapse problem. Based on the theoretical analysis, we propose that the nonlinearity is also very important for language models, which is usually studied in convolutional neural networks for vision tasks. The series informed activation function is then introduced with tiny calculations that can be ignored, and an augmented shortcut is further used to enhance the model nonlinearity. We then demonstrate that the proposed approach is significantly effective for enhancing the model nonlinearity through carefully designed ablations; thus, we present a new efficient model architecture for establishing modern, namely, PanGu-$\pi$. Experiments are then conducted using the same dataset and training strategy to compare PanGu-$\pi$ with state-of-the-art LLMs. The results show that PanGu-$\pi$-7B can achieve a comparable performance to that of benchmarks with about 10\% inference speed-up, and PanGu-$\pi$-1B can achieve state-of-the-art performance in terms of accuracy and efficiency. In addition, we have deployed PanGu-$\pi$-7B in the high-value domains of finance and law, developing an LLM named YunShan for practical application. The results show that YunShan can surpass other models with similar scales on benchmarks.

Computational notebooks such as Jupyter are popular for exploratory data analysis and insight finding. Despite the module-based structure, notebooks visually appear as a single thread of interleaved cells containing text, code, visualizations, and tables, which can be unorganized and obscure users' data analysis workflow. Furthermore, users with limited coding expertise may struggle to quickly engage in the analysis process. In this work, we design and implement an interactive notebook framework, WHATSNEXT, with the goal of supporting low-code visual data exploration with insight-based user guidance. In particular, we (1) re-design a standard notebook cell to include a recommendation panel that suggests possible next-step exploration questions or analysis actions to take, and (2) create an interactive, dynamic tree visualization that reflects the analytic dependencies between notebook cells to make it easy for users to see the structure of the data exploration threads and trace back to previous steps., Comment: to appear in VL/HCC 2023

To facilitate the reuse of existing charts, previous research has examined how to obtain a semantic understanding of a chart by deconstructing its visual representation into reusable components, such as encodings. However, existing deconstruction approaches primarily focus on chart styles, handling only basic layouts. In this paper, we investigate how to deconstruct chart layouts, focusing on rectangle-based ones, as they cover not only 17 chart types but also advanced layouts (e.g., small multiples, nested layouts). We develop an interactive tool, called Mystique, adopting a mixed-initiative approach to extract the axes and legend, and deconstruct a chart's layout into four semantic components: mark groups, spatial relationships, data encodings, and graphical constraints. Mystique employs a wizard interface that guides chart authors through a series of steps to specify how the deconstructed components map to their own data. On 150 rectangle-based SVG charts, Mystique achieves above 85% accuracy for axis and legend extraction and 96% accuracy for layout deconstruction. In a chart reproduction study, participants could easily reuse existing charts on new datasets. We discuss the current limitations of Mystique and future research directions., Comment: To appear at the 2023 IEEE Visualization Conference

The Origin-Destination~(OD) networks provide an estimation of the flow of people from every region to others in the city, which is an important research topic in transportation, urban simulation, etc. Given structural regional urban features, generating the OD network has become increasingly appealing to many researchers from diverse domains. However, existing works are limited in independent generation of each OD pair, i.e., flow of people from one region to another, overlooking the relations within the overall network. In this paper, we instead propose to generate the OD network, and design a graph denoising diffusion method to learn the conditional joint probability distribution of the nodes and edges within the OD network given city characteristics at region level. To overcome the learning difficulty of the OD networks covering over thousands of regions, we decompose the original one-shot generative modeling of the diffusion model into two cascaded stages, corresponding to the generation of network topology and the weights of edges, respectively. To further reproduce important network properties contained in the city-wide OD network, we design an elaborated graph denoising network structure including a node property augmentation module and a graph transformer backbone. Empirical experiments on data collected in three large US cities have verified that our method can generate OD matrices for new cities with network statistics remarkably similar with the ground truth, further achieving superior outperformance over competitive baselines in terms of the generation realism., Comment: 11 pagers, 5 figures

Real-world event sequences are often complex and heterogeneous, making it difficult to create meaningful visualizations using simple data aggregation and visual encoding techniques. Consequently, visualization researchers have developed numerous visual summarization techniques to generate concise overviews of sequential data. These techniques vary widely in terms of summary structures and contents, and currently there is a knowledge gap in understanding the effectiveness of these techniques. In this work, we present the design and results of an insight-based crowdsourcing experiment evaluating three existing visual summarization techniques: CoreFlow, SentenTree, and Sequence Synopsis. We compare the visual summaries generated by these techniques across three tasks, on six datasets, at six levels of granularity. We analyze the effects of these variables on summary quality as rated by participants and completion time of the experiment tasks. Our analysis shows that Sequence Synopsis produces the highest-quality visual summaries for all three tasks, but understanding Sequence Synopsis results also takes the longest time. We also find that the participants evaluate visual summary quality based on two aspects: content and interpretability. We discuss the implications of our findings on developing and evaluating new visual summarization techniques.

We present a state-of-the-art report on visualization corpora in automated chart analysis research. We survey 56 papers that created or used a visualization corpus as the input of their research techniques or systems. Based on a multi-level task taxonomy that identifies the goal, method, and outputs of automated chart analysis, we examine the property space of existing chart corpora along five dimensions: format, scope, collection method, annotations, and diversity. Through the survey, we summarize common patterns and practices of creating chart corpora, identify research gaps and opportunities, and discuss the desired properties of future benchmark corpora and the required tools to create them., Comment: To appear at EuroVis 2023

In speech translation, leveraging multimodal data to improve model performance and address limitations of individual modalities has shown significant effectiveness. In this paper, we harness the complementary strengths of speech and text, which are disparate modalities. We observe three levels of modality gap between them, denoted by Modal input representation, Modal semantic, and Modal hidden states. To tackle these gaps, we propose \textbf{F}use-\textbf{S}peech-\textbf{T}ext (\textbf{FST}), a cross-modal model which supports three distinct input modalities for translation: speech, text, and fused speech-text. We leverage multiple techniques for cross-modal alignment and conduct a comprehensive analysis to assess its impact on speech translation, machine translation, and fused speech-text translation. We evaluate FST on MuST-C, GigaST, and newstest benchmark. Experiments show that the proposed FST achieves an average 34.0 BLEU on MuST-C En$\rightarrow$De/Es/Fr (vs SOTA +1.1 BLEU). Further experiments demonstrate that FST does not degrade on MT task, as observed in prior works. Instead, it yields an average improvement of 3.2 BLEU over the pre-trained MT model.

Business users perform data analysis to inform decisions for improving business processes and outcomes despite having limited formal technical training. While earlier work has focused on data analysts' and data scientists' practices and challenges, little is known about business users' decision-making practices and how they incorporate data and visual analytics into their workflows. To address this gap, we first conduct an interview study with 22 business users to understand the general practices and challenges in their data-driven decision-making processes. We contribute an end-to-end model of business users' data-driven decision-making processes elaborating the tasks, tools, and challenges at each stage. We find that business users analyze data without relying on data analysts due to various practical constraints and considerations. However, their existing tools are inadequate, particularly in helping understand the relationship between data variables and business goals and facilitating the exploration of what-if scenarios. These findings suggest a need for advanced predictive and prescriptive analytics (PPA) tools to support what-if analysis. Motivated by this need, we perform a follow-up, task-based study to understand PPA's role and potential in business users' decision-making processes. We find that PPA helps improve efficiency and confidence in decision-making. However, business users also believe that PPA-powered what-if analysis tools are currently in their nascent stages and report improvements before fully integrating them into their decision-making processes. Building upon these findings, we discuss the opportunities and challenges in incorporating PPA into data-driven decision-making and its implications for future data and visual analytics systems., Comment: Submitted to IEEE TVCG

Maximizing a DR-submodular function subject to a general convex set is an NP-hard problem arising from many applications in combinatorial optimization and machine learning. While it is highly desirable to design efficient approximation algorithms under this general setting where neither the objective function is monotonic nor the feasible set is down-closed, our main contribution is to present a 0.25-approximation Frank-Wolfe type of algorithm with a sub-exponential time-complexity under the value oracle model., Comment: 8 Pages

Providing efficient human mobility services and infrastructure is one of the major concerns of most mid-sized to large cities around the world. A proper understanding of the dynamics of commuting flows is, therefore, a requisite to better plan urban areas. In this context, an important task is to study hypothetical scenarios in which possible future changes are evaluated. For instance, how the increase in residential units or transportation modes in a neighborhood will change the commuting flows to or from that region? In this paper, we propose to leverage GMEL, a recently introduced graph neural network model, to evaluate changes in commuting flows taking into account different land use and infrastructure scenarios. We validate the usefulness of our methodology through real-world case studies set in two large cities in Brazil., Comment: Presented at the 10th International Workshop on Urban Computing, 2021

This paper describes the systems submitted to IWSLT 2021 by the Volctrans team. We participate in the offline speech translation and text-to-text simultaneous translation tracks. For offline speech translation, our best end-to-end model achieves 8.1 BLEU improvements over the benchmark on the MuST-C test set and is even approaching the results of a strong cascade solution. For text-to-text simultaneous translation, we explore the best practice to optimize the wait-k model. As a result, our final submitted systems exceed the benchmark at around 7 BLEU on the same latency regime. We will publish our code and model to facilitate both future research works and industrial applications. This paper describes the systems submitted to IWSLT 2021 by the Volctrans team. We participate in the offline speech translation and text-to-text simultaneous translation tracks. For offline speech translation, our best end-to-end model achieves 7.9 BLEU improvements over the benchmark on the MuST-C test set and is even approaching the results of a strong cascade solution. For text-to-text simultaneous translation, we explore the best practice to optimize the wait-k model. As a result, our final submitted systems exceed the benchmark at around 7 BLEU on the same latency regime. We release our code and model at \url{https://github.com/bytedance/neurst/tree/master/examples/iwslt21} to facilitate both future research works and industrial applications., Comment: IWSLT 2021

Graphs are playing a crucial role in different fields since they are powerful tools to unveil intrinsic relationships among signals. In many scenarios, an accurate graph structure representing signals is not available at all and that motivates people to learn a reliable graph structure directly from observed signals. However, in real life, it is inevitable that there exists uncertainty in the observed signals due to noise measurements or limited observability, which causes a reduction in reliability of the learned graph. To this end, we propose a graph learning framework using Wasserstein distributionally robust optimization (WDRO) which handles uncertainty in data by defining an uncertainty set on distributions of the observed data. Specifically, two models are developed, one of which assumes all distributions in uncertainty set are Gaussian distributions and the other one has no prior distributional assumption. Instead of using interior point method directly, we propose two algorithms to solve the corresponding models and show that our algorithms are more time-saving. In addition, we also reformulate both two models into Semi-Definite Programming (SDP), and illustrate that they are intractable in the scenario of large-scale graph. Experiments on both synthetic and real world data are carried out to validate the proposed framework, which show that our scheme can learn a reliable graph in the context of uncertainty., Comment: 21 pages,9 figures