Table-to-text generation aims at automatically generating text to help people conveniently obtain salient information in tables. Recent works explicitly decompose the generation process into content planning and surface generation stages, employing two autoregressive networks for them respectively. However, they are computationally expensive due to the non-parallelizable nature of autoregressive decoding and the redundant parameters of two networks. In this paper, we propose the first totally non-autoregressive table-to-text model (Plan-then-Seam, PTS) that produces its outputs in parallel with one single network. PTS firstly writes and calibrates one plan of the content to be generated with a novel rethinking pointer predictor, and then takes the plan as the context for seaming to decode the description. These two steps share parameters and perform iteratively to capture token inter-dependency while keeping parallel decoding. Experiments on two public benchmarks show that PTS achieves 3.0~5.6 times speedup for inference time, reducing 50% parameters, while maintaining as least comparable performance against strong two-stage table-to-text competitors.

Time series is the most prevalent form of input data for educational prediction tasks. The vast majority of research using time series data focuses on hand-crafted features, designed by experts for predictive performance and interpretability. However, extracting these features is labor-intensive for humans and computers. In this paper, we propose an approach that utilizes irregular multivariate time series modeling with graph neural networks to achieve comparable or better accuracy with raw time series clickstreams in comparison to hand-crafted features. Furthermore, we extend concept activation vectors for interpretability in raw time series models. We analyze these advances in the education domain, addressing the task of early student performance prediction for downstream targeted interventions and instructional support. Our experimental analysis on 23 MOOCs with millions of combined interactions over six behavioral dimensions show that models designed with our approach can (i) beat state-of-the-art educational time series baselines with no feature extraction and (ii) provide interpretable insights for personalized interventions. Source code: https://github.com/epfl-ml4ed/ripple/.

Every time a new application of AI is announced, I feel a short-lived rush of excitement -- followed soon after by a knot in my stomach. This is because I know the technology, more often than not, hasn't been designed with equity in mind. One system, ChatGPT, has reached 100 million unique users just two months after its launch. The text-based tool engages users in interactive, friendly, AI-generated exchanges with a chatbot that has been developed to speak authoritatively on any subject it's prompted to address. In an interview with Michael Barbaro on the The Daily podcast from the New York Times, tech reporter Kevin Roose described how an app similar to ChatGPT, Bing's AI chatbot, which also is built on OpenAI's GPT-3 language model, responded to his request for a suggestion on a side dish to accompany French onion soup for Valentine's Day dinner with his wife.

Like so many cities before it, Phoenix went all out to host the Super Bowl earlier this month. Expecting about 1 million fans to come to town for the biggest American sporting event of the year, the city rolled out a fleet of self-driving electric vehicles to ferry visitors from the airport. Robots sifted through the trash to pull out anything that could be composted. There were less visible developments, too. In preparation for the game, the local authorities upgraded a network of cameras around the city's downtown--and have kept them running after the spectators have left.

If you read my work you probably know that I publish my articles first and foremost in my AI newsletter, The Algorithmic Bridge. What you may not know is that every Sunday I publish a special column I call "what you may have missed," where I review everything that has happened during the week with analyses that help you make sense of the news. Semafor reported two weeks ago that, if everything goes according to the plan, Microsoft will close a $10B investment deal with OpenAI before the end of January (Satya Nadella, Microsoft's CEO, announced the extended partnership officially on Monday). There's been some misinformation about the deal which implied that OpenAI execs weren't sure about the company's long-term viability. Leo L'Orange, who writes The Neuron, explains that "once $92 billion in profit plus $13 billion in initial investment are repaid to Microsoft and once the other venture investors earn $150 billion, all of the equity reverts back to OpenAI."

By explaining how humans would solve a given task, human rationales can provide strong learning signal for neural language models (LMs). Explanation regularization (ER) aims to improve LM generalization by pushing the LM's machine rationales (Which input tokens did the LM focus on?) to align with human rationales (Which input tokens would humans focus on?). Though prior works primarily study ER via in-distribution (ID) evaluation, out-of-distribution (OOD) generalization is often more critical in real-world scenarios, yet ER's effect on OOD generalization has been underexplored. In this paper, we introduce ER-Test, a framework for evaluating ER models' OOD generalization along three dimensions: unseen dataset tests, contrast set tests, and functional tests. Using ER-Test, we extensively analyze how ER models' OOD generalization varies with different ER design choices. Across two tasks and six datasets, ER-Test shows that ER has little impact on ID performance but can yield large OOD performance gains. Also, we find that ER can improve OOD performance even with limited rationale supervision. ER-Test's results help demonstrate ER's utility and establish best practices for using ER effectively.

Binary geospatial data is commonly analyzed with generalized linear mixed models, specified with a linear fixed covariate effect and a Gaussian Process (GP)-distributed spatial random effect, relating to the response via a link function. The assumption of linear covariate effects is severely restrictive. Random Forests (RF) are increasingly being used for non-linear modeling of spatial data, but current extensions of RF for binary spatial data depart the mixed model setup, relinquishing inference on the fixed effects and other advantages of using GP. We propose RF-GP, using Random Forests for estimating the non-linear covariate effect and Gaussian Processes for modeling the spatial random effects directly within the generalized mixed model framework. We observe and exploit equivalence of Gini impurity measure and least squares loss to propose an extension of RF for binary data that accounts for the spatial dependence. We then propose a novel link inversion algorithm that leverages the properties of GP to estimate the covariate effects and offer spatial predictions. RF-GP outperforms existing RF methods for estimation and prediction in both simulated and real-world data. We establish consistency of RF-GP for a general class of $\beta$-mixing binary processes that includes common choices like spatial Mat\'ern GP and autoregressive processes.

Cybersecurity vendors consistently apply AI (Artificial Intelligence) to their solutions and many cybersecurity domains can benefit from AI technology. However, black-box AI techniques present some difficulties in comprehension and adoption by its operators, given that their decisions are not always humanly understandable (as is usually the case with deep neural networks, for example). Since it aims to make the operation of AI algorithms more interpretable for its users and developers, XAI (eXplainable Artificial Intelligence) can be used to address this issue. Through a systematic literature review, this work seeks to investigate the current research scenario on XAI applied to cybersecurity, aiming to discover which XAI techniques have been applied in cybersecurity, and which areas of cybersecurity have already benefited from this technology.

With the widespread use of knowledge graphs (KG) in various automated AI systems and applications, it is very important to ensure that information retrieval algorithms leveraging them are free from societal biases. Previous works have depicted biases that persist in KGs, as well as employed several metrics for measuring the biases. However, such studies lack the systematic exploration of the sensitivity of the bias measurements, through varying sources of data, or the embedding algorithms used. To address this research gap, in this work, we present a holistic analysis of bias measurement on the knowledge graph. First, we attempt to reveal data biases that surface in Wikidata for thirteen different demographics selected from seven continents. Next, we attempt to unfold the variance in the detection of biases by two different knowledge graph embedding algorithms - TransE and ComplEx. We conduct our extensive experiments on a large number of occupations sampled from the thirteen demographics with respect to the sensitive attribute, i.e., gender. Our results show that the inherent data bias that persists in KG can be altered by specific algorithm bias as incorporated by KG embedding learning algorithms. Further, we show that the choice of the state-of-the-art KG embedding algorithm has a strong impact on the ranking of biased occupations irrespective of gender. We observe that the similarity of the biased occupations across demographics is minimal which reflects the socio-cultural differences around the globe. We believe that this full-scale audit of the bias measurement pipeline will raise awareness among the community while deriving insights related to design choices of data and algorithms both and refrain from the popular dogma of ``one-size-fits-all''.

In this work, we tackle two vital tasks in automated driving systems, i.e., driver intent prediction and risk object identification from egocentric images. Mainly, we investigate the question: what would be good road scene-level representations for these two tasks? We contend that a scene-level representation must capture higher-level semantic and geometric representations of traffic scenes around ego-vehicle while performing actions to their destinations. To this end, we introduce the representation of semantic regions, which are areas where ego-vehicles visit while taking an afforded action (e.g., left-turn at 4-way intersections). We propose to learn scene-level representations via a novel semantic region prediction task and an automatic semantic region labeling algorithm. Extensive evaluations are conducted on the HDD and nuScenes datasets, and the learned representations lead to state-of-the-art performance for driver intention prediction and risk object identification.