Transfer learning has led to large gains in performance for nearly all NLP tasks while making downstream models easier and faster to train. This has also been extended to low-resourced languages, with some success. We investigate the properties of cross-lingual transfer learning between ten low-resourced languages, from the perspective of a named entity recognition task. We specifically investigate how much adaptive fine-tuning and the choice of transfer language affect zero-shot transfer performance. We find that models that perform well on a single language often do so at the expense of generalising to others, while models with the best generalisation to other languages suffer in individual language performance. Furthermore, the amount of data overlap between the source and target datasets is a better predictor of transfer performance than either the geographical or genetic distance between the languages.

A family member's hurried Google search for a last-second visa to visit New Zealand recently caused a headache--and provided a timely reminder of why Google faces a landmark US antitrust trial next week. Tapping on the first link took us off to a website that after a few swipes charged $118 for the necessary paperwork. Only later did it emerge that we'd paid a so-called "internet-based travel technology company" and not a government agency, and been fleeced for more than double the required cost. Fortunately, our panicked refund demand was fulfilled, but the miscue highlights a major frustration with Google that helped land it in court. The stacks of ads above its search results, like the visa link we clicked on, too often knock users off course from the information that they are seeking.

This study presents insights from interviews with nineteen Knowledge Graph (KG) practitioners who work in both enterprise and academic settings on a wide variety of use cases. Through this study, we identify critical challenges experienced by KG practitioners when creating, exploring, and analyzing KGs that could be alleviated through visualization design. Our findings reveal three major personas among KG practitioners - KG Builders, Analysts, and Consumers - each of whom have their own distinct expertise and needs. We discover that KG Builders would benefit from schema enforcers, while KG Analysts need customizable query builders that provide interim query results. For KG Consumers, we identify a lack of efficacy for node-link diagrams, and the need for tailored domain-specific visualizations to promote KG adoption and comprehension. Lastly, we find that implementing KGs effectively in practice requires both technical and social solutions that are not addressed with current tools, technologies, and collaborative workflows. From the analysis of our interviews, we distill several visualization research directions to improve KG usability, including knowledge cards that balance digestibility and discoverability, timeline views to track temporal changes, interfaces that support organic discovery, and semantic explanations for AI and machine learning predictions.

Modern vision models typically rely on fine-tuning general-purpose models pre-trained on large, static datasets. These general-purpose models only capture the knowledge within their pre-training datasets, which are tiny, out-of-date snapshots of the Internet -- where billions of images are uploaded each day. We suggest an alternate approach: rather than hoping our static datasets transfer to our desired tasks after large-scale pre-training, we propose dynamically utilizing the Internet to quickly train a small-scale model that does extremely well on the task at hand. Our approach, called Internet Explorer, explores the web in a self-supervised manner to progressively find relevant examples that improve performance on a desired target dataset. It cycles between searching for images on the Internet with text queries, self-supervised training on downloaded images, determining which images were useful, and prioritizing what to search for next. We evaluate Internet Explorer across several datasets and show that it outperforms or matches CLIP oracle performance by using just a single GPU desktop to actively query the Internet for 30--40 hours. Results, visualizations, and videos at https://internet-explorer-ssl.github.io/

Keeping up with research and finding related work is still a time-consuming task for academics. Researchers sift through thousands of studies to identify a few relevant ones. Automation techniques can help by increasing the efficiency and effectiveness of this task. To this end, we developed CRUISE-Screening, a web-based application for conducting living literature reviews - a type of literature review that is continuously updated to reflect the latest research in a particular field. CRUISE-Screening is connected to several search engines via an API, which allows for updating the search results periodically. Moreover, it can facilitate the process of screening for relevant publications by using text classification and question answering models. CRUISE-Screening can be used both by researchers conducting literature reviews and by those working on automating the citation screening process to validate their algorithms. The application is open-source: https://github.com/ProjectDoSSIER/cruise-screening, and a demo is available under this URL: https://citation-screening.ec.tuwien.ac.at. We discuss the limitations of our tool in Appendix A.

A much-demanded feature is finally coming to Threads very soon, Meta CEO Mark Zuckerberg has confirmed. A keyword search function is on the way. Until now, the search box has only been useful for looking up user accounts. In fact, the company is already testing the function in Australia and New Zealand. It plans to roll out keyword search more broadly to English-speaking territories in short order.

Quality-sensitive applications of machine learning (ML) require quality assurance (QA) by humans before the predictions of an ML model can be deployed. QA for ML (QA4ML) interfaces require users to view a large amount of data and perform many interactions to correct errors made by the ML model. An optimized user interface (UI) can significantly reduce interaction costs. While UI optimization can be informed by user studies evaluating design options, this approach is not scalable because there are typically numerous small variations that can affect the efficiency of a QA4ML interface. Hence, we propose using simulation to evaluate and aid the optimization of QA4ML interfaces. In particular, we focus on simulating the combined effects of human intelligence in initiating appropriate interaction commands and machine intelligence in providing algorithmic assistance for accelerating QA4ML processes. As QA4ML is usually labor-intensive, we use the simulated task completion time as the metric for UI optimization under different interface and algorithm setups. We demonstrate the usage of this UI design method in several QA4ML applications.

The scale and complexity of workloads in modern cloud services have brought into sharper focus a critical challenge in automated index tuning -- the need to recommend high-quality indexes while maintaining index tuning scalability. This challenge is further compounded by the requirement for automated index implementations to introduce minimal query performance regressions in production deployments, representing a significant barrier to achieving scalability and full automation. This paper directs attention to these challenges within automated index tuning and explores ways in which machine learning (ML) techniques provide new opportunities in their mitigation. In particular, we reflect on recent efforts in developing ML techniques for workload selection, candidate index filtering, speeding up index configuration search, reducing the amount of query optimizer calls, and lowering the chances of performance regressions. We highlight the key takeaways from these efforts and underline the gaps that need to be closed for their effective functioning within the traditional index tuning framework. Additionally, we present a preliminary cross-platform design aimed at democratizing index tuning across multiple SQL-like systems -- an imperative in today's continuously expanding data system landscape. We believe our findings will help provide context and impetus to the research and development efforts in automated index tuning.

Joint entity and relation extraction is the fundamental task of information extraction, consisting of two subtasks: named entity recognition and relation extraction. Most existing joint extraction methods suffer from issues of feature confusion or inadequate interaction between two subtasks. In this work, we propose a Co-Attention network for joint entity and Relation Extraction (CARE). Our approach involves learning separate representations for each subtask, aiming to avoid feature overlap. At the core of our approach is the co-attention module that captures two-way interaction between two subtasks, allowing the model to leverage entity information for relation prediction and vice versa, thus promoting mutual enhancement. Extensive experiments on three joint entity-relation extraction benchmark datasets (NYT, WebNLG and SciERC) show that our proposed model achieves superior performance, surpassing existing baseline models.

For visual document understanding (VDU), self-supervised pretraining has been shown to successfully generate transferable representations, yet, effective adaptation of such representations to distribution shifts at test-time remains to be an unexplored area. We propose DocTTA, a novel test-time adaptation method for documents, that does source-free domain adaptation using unlabeled target document data. DocTTA leverages cross-modality self-supervised learning via masked visual language modeling, as well as pseudo labeling to adapt models learned on a \textit{source} domain to an unlabeled \textit{target} domain at test time. We introduce new benchmarks using existing public datasets for various VDU tasks, including entity recognition, key-value extraction, and document visual question answering. DocTTA shows significant improvements on these compared to the source model performance, up to 1.89\% in (F1 score), 3.43\% (F1 score), and 17.68\% (ANLS score), respectively. Our benchmark datasets are available at \url{https://saynaebrahimi.github.io/DocTTA.html}.