Collecting high quality conversational data can be very expensive for most applications and infeasible for others due to privacy, ethical, or similar concerns. A promising direction to tackle this problem is to generate synthetic dialogues by prompting large language models. In this work, we use a small set of expert-written conversations as in-context examples to synthesize a social conversation dataset using prompting. We perform several thorough evaluations of our synthetic conversations compared to human-collected conversations. This includes various dimensions of conversation quality with human evaluation directly on the synthesized conversations, and interactive human evaluation of chatbots fine-tuned on the synthetically generated dataset. We additionally demonstrate that this prompting approach is generalizable to multi-party conversations, providing potential to create new synthetic data for multi-party tasks. Our synthetic multi-party conversations were rated more favorably across all measured dimensions compared to conversation excerpts sampled from a human-collected multi-party dataset.

In active learning, acquisition functions define informativeness directly on the representation position within the model manifold. However, for most machine learning models (in particular neural networks) this representation is not fixed due to the training pool fluctuations in between active learning rounds. Therefore, several popular strategies are sensitive to experiment parameters (e.g. architecture) and do not consider model robustness to out-of-distribution settings. To alleviate this issue, we propose a grounded second-order definition of information content and sample importance within the context of active learning. Specifically, we define importance by how often a neural network "forgets" a sample during training - artifacts of second order representation shifts. We show that our definition produces highly accurate importance scores even when the model representations are constrained by the lack of training data. Motivated by our analysis, we develop Gaussian Switch Sampling (GauSS). We show that GauSS is setup agnostic and robust to anomalous distributions with exhaustive experiments on three in-distribution benchmarks, three out-of-distribution benchmarks, and three different architectures. We report an improvement of up to 5% when compared against four popular query strategies.

Many practical applications, ranging from paper-reviewer assignment in peer review to job-applicant matching for hiring, require human decision makers to identify relevant matches by combining their expertise with predictions from machine learning models. In many such model-assisted document matching tasks, the decision makers have stressed the need for assistive information about the model outputs (or the data) to facilitate their decisions. In this paper, we devise a proxy matching task that allows us to evaluate which kinds of assistive information improve decision makers' performance (in terms of accuracy and time). Through a crowdsourced (N=271 participants) study, we find that providing black-box model explanations reduces users' accuracy on the matching task, contrary to the commonly-held belief that they can be helpful by allowing better understanding of the model. On the other hand, custom methods that are designed to closely attend to some task-specific desiderata are found to be effective in improving user performance. Surprisingly, we also find that the users' perceived utility of assistive information is misaligned with their objective utility (measured through their task performance).

Abstract: Query by Example is a well-known information retrieval task in which a document is chosen by the user as the search query and the goal is to retrieve relevant documents from a large collection. However, a document often covers multiple aspects of a topic. To address this scenario we introduce the task of faceted Query by Example in which users can also specify a finer grained aspect in addition to the input query document. We focus on the application of this task in scientific literature search. We envision models which are able to retrieve scientific papers analogous to a query scientific paper along specifically chosen rhetorical structure elements as one solution to this problem.

The World Customs Organization (WCO) recently conducted a BACUDA Data Analytics workshop for the Maldives Customs Service with 41 participants from the 30th of January to the 1st of February in Male, Maldives. The mission was financed by the Customs Cooperation Fund of Korea (CCF-Korea) and took place under the WCO's BACUDA initiative, the WCO capacity building project on Data Analytics. WCO experts and two BACUDA Scholarship graduates led the workshop. They delivered various sessions to equip the customs officials with the latest data analytics tools and techniques. One of the key highlights of the workshop was a hands-on session where the participants learned how to use Python language to work with the AI HS algorithm developed through the BACUDA project.

I was amazed last August, when I first asked GPT-3 to write a sample article about the impact of GPT on higher education. It responded with an accurate, cogent 700-word piece in just seconds. I wrote then that "higher ed will never be the same!" However, the models and interfaces continued to improve with the GPT-3.5 and ChatGPT. We have now embarked on an ever-accelerating improvement of the technology, fueled by tens of billions of dollars of investment and a hot competition--most notably between Microsoft/Bing and Alphabet/Google.

If the boxy Opportunity rover could elicit years of anthropomorphized love and goodwill, then surely Earthlings will warm to the idea of sending a snake-shaped robot to the moon. This robot--the brainchild of students at Northeastern University--is meant to wiggle across difficult terrain, measure water in the pit of craters, and bite its own tail to become a spinning ouroboros tumbling down the side of a lunar cliff. NASA's annual Big Idea Challenge presents a new query each year that's geared toward an engineering problem the agency needs to solve. In fall 2021, students from universities across the United States set out to design a robot that could survive extreme lunar terrain and send data back to Earth. The winning team, of students from Northeastern's Students for the Exploration and Development of Space club, took home the top prize in November and now hope to turn their winning design into an advanced prototype that could actually be sent to the moon.

TL;DR: A new study has found that playing video games can improve certain cognitive skills such as problem solving, memory, and attention. The study was conducted with a group of people who had never previously played video games and the results have been promising. Playing games can be beneficial for those looking to improve their mental skills. If you're a business owner looking to increase the productivity and efficiency of your workflows, you should consider utilizing automation. Automation is a process that allows for the automation of certain tasks or processes.

"I observed assistive technologies -- developed by scientists and engineers my friends and I never met -- which liberated us. My dream has always been to be one of those engineers." Before James Hermus started elementary school, he was a happy, curious kid who loved to learn. By the end of first grade, however, all that started to change, he says. As his schoolbooks became more advanced, Hermus could no longer memorize the words on each page, and pretend to be reading.