While there has been substantial progress in developing systems to automate fact-checking, they still lack credibility in the eyes of the users. Thus, an interesting approach has emerged: to perform automatic fact-checking by verifying whether an input claim has been previously fact-checked by professional fact-checkers and to return back an article that explains their decision. This is a sensible approach as people trust manual fact-checking, and as many claims are repeated multiple times. Yet, a major issue when building such systems is the small number of known tweet--verifying article pairs available for training. Here, we aim to bridge this gap by making use of crowd fact-checking, i.e., mining claims in social media for which users have responded with a link to a fact-checking article. In particular, we mine a large-scale collection of 330,000 tweets paired with a corresponding fact-checking article. We further propose an end-to-end framework to learn from this noisy data based on modified self-adaptive training, in a distant supervision scenario. Our experiments on the CLEF'21 CheckThat! test set show improvements over the state of the art by two points absolute. Our code and datasets are available at https://github.com/mhardalov/crowdchecked-claims

Despite decades of research on authorship attribution (AA) and authorship verification (AV), inconsistent dataset splits/filtering and mismatched evaluation methods make it difficult to assess the state of the art. In this paper, we present a survey of the fields, resolve points of confusion, introduce Valla that standardizes and benchmarks AA/AV datasets and metrics, provide a large-scale empirical evaluation, and provide apples-to-apples comparisons between existing methods. We evaluate eight promising methods on fifteen datasets (including distribution-shifted challenge sets) and introduce a new large-scale dataset based on texts archived by Project Gutenberg. Surprisingly, we find that a traditional Ngram-based model performs best on 5 (of 7) AA tasks, achieving an average macro-accuracy of $76.50\%$ (compared to $66.71\%$ for a BERT-based model). However, on the two AA datasets with the greatest number of words per author, as well as on the AV datasets, BERT-based models perform best. While AV methods are easily applied to AA, they are seldom included as baselines in AA papers. We show that through the application of hard-negative mining, AV methods are competitive alternatives to AA methods. Valla and all experiment code can be found here: https://github.com/JacobTyo/Valla

Standard approaches to hate speech detection rely on sufficient available hate speech annotations. Extending previous work that repurposes natural language inference (NLI) models for zero-shot text classification, we propose a simple approach that combines multiple hypotheses to improve English NLI-based zero-shot hate speech detection. We first conduct an error analysis for vanilla NLI-based zero-shot hate speech detection and then develop four strategies based on this analysis. The strategies use multiple hypotheses to predict various aspects of an input text and combine these predictions into a final verdict. We find that the zero-shot baseline used for the initial error analysis already outperforms commercial systems and fine-tuned BERT-based hate speech detection models on HateCheck. The combination of the proposed strategies further increases the zero-shot accuracy of 79.4% on HateCheck by 7.9 percentage points (pp), and the accuracy of 69.6% on ETHOS by 10.0pp.

There are those who debate whether the new decade of the 2020s commenced on 1 Jan 2020 or 1 Jan 2021. Either way, one suspects that many around the world will hope that at some point during the course of 2021 the current year will mark a shift away from the events of 2020 and allow for a new start. For a definition of AI, Machine Learning and Deep Learning see the Article an Intro to AI. A new administration is in place in the US and the talk is about a major push for Green Technology and the need to stimulate next generation infrastructure including AI and 5G to generate economic recovery with David Knight forecasting that 5G has the potential - the potential - to drive GDP growth of 40% or more by 2030. The Biden administration has stated that it will boost spending in emerging technologies that includes AI and 5G to $300Bn over a four year period. On the other side of the Atlantic Ocean, the EU have announced a Green Deal and also need to consider the European AI policy to develop next generation companies that will drive economic growth and employment.

Smart energy performance monitoring and optimisation at the supplier and consumer levels is essential to realising smart cities. In order to implement a more sustainable energy management plan, it is crucial to conduct a better energy forecast. The next-generation smart meters can also be used to measure, record, and report energy consumption data, which can be used to train machine learning (ML) models for predicting energy needs. However, sharing fine-grained energy data and performing centralised learning may compromise users' privacy and leave them vulnerable to several attacks. This study addresses this issue by utilising federated learning (FL), an emerging technique that performs ML model training at the user level, where data resides. We introduce FedTrees, a new, lightweight FL framework that benefits from the outstanding features of ensemble learning. Furthermore, we developed a delta-based early stopping algorithm to monitor FL training and stop it when it does not need to continue. The simulation results demonstrate that FedTrees outperforms the most popular federated averaging (FedAvg) framework and the baseline Persistence model for providing accurate energy forecasting patterns while taking only 2% of the computation time and 13% of the communication rounds compared to FedAvg, saving considerable amounts of computation and communication resources.

Spaceborne synthetic aperture radar (SAR) can provide accurate images of the ocean surface roughness day-or-night in nearly all weather conditions, being an unique asset for many geophysical applications. Considering the huge amount of data daily acquired by satellites, automated techniques for physical features extraction are needed. Even if supervised deep learning methods attain state-of-the-art results, they require great amount of labeled data, which are difficult and excessively expensive to acquire for ocean SAR imagery. To this end, we use the subaperture decomposition (SD) algorithm to enhance the unsupervised learning retrieval on the ocean surface, empowering ocean researchers to search into large ocean databases. We empirically prove that SD improve the retrieval precision with over 20% for an unsupervised transformer auto-encoder network. Moreover, we show that SD brings important performance boost when Doppler centroid images are used as input data, leading the way to new unsupervised physics guided retrieval algorithms.

This paper presents Macquarie University's participation to the two most recent BioASQ Synergy Tasks (as per June 2022), and to the BioASQ10 Task~B (BioASQ10b), Phase~B. In these tasks, participating systems are expected to generate complex answers to biomedical questions, where the answers may contain more than one sentence. We apply query-focused extractive summarisation techniques. In particular, we follow a sentence classification-based approach that scores each candidate sentence associated to a question, and the $n$ highest-scoring sentences are returned as the answer. The Synergy Task corresponds to an end-to-end system that requires document selection, snippet selection, and finding the final answer, but it has very limited training data. For the Synergy task, we selected the candidate sentences following two phases: document retrieval and snippet retrieval, and the final answer was found by using a DistilBERT/ALBERT classifier that had been trained on the training data of BioASQ9b. Document retrieval was achieved as a standard search over the CORD-19 data using the search API provided by the BioASQ organisers, and snippet retrieval was achieved by re-ranking the sentences of the top retrieved documents, using the cosine similarity of the question and candidate sentence. We observed that vectors represented via sBERT have an edge over tf.idf. BioASQ10b Phase B focuses on finding the specific answers to biomedical questions. For this task, we followed a data-centric approach. We hypothesised that the training data of the first BioASQ years might be biased and we experimented with different subsets of the training data. We observed an improvement of results when the system was trained on the second half of the BioASQ10b training data.

A "MALICIOUS" artificial intelligence bot that wrote a paper about itself could trigger World War III unless governments immediately curb its growing power, an expert has warned. AI and blockchain technology expert Herbert Sim said that the creation of GPT-3 - a program that can produce text indistinguishable from human writing - in 2020 had "opened Pandora's box". The tech expert warned that while certain groups and political oppositions could tap into using "troll bots" to undermine governments and spread fake news, their risks stretched much further. However, left unchecked, Sims claims the programs could use their "intelligence" to write malware and even weaponize drones and bioweapons, becoming lethal autonomous weapons (LAWs). "AI has helped technology shift forward hugely in recent decades, and undoubtedly there are lots of benefits to be reaped from it," he said.

"Can a robot write a symphony? Can a robot turn a canvas into a beautiful masterpiece?" So asks Will Smith in the 2004 movie iRobot. Of course, the answer back then was a resounding'no', however, 15 years later it's not so simple. An AI rapper has already been signed to a record label.

We consider preference disaggregation in the context of multiple criteria sorting. The value function parameters and thresholds separating the classes are inferred from the Decision Maker's (DM's) assignment examples. Given the multiplicity of sorting models compatible with indirect preferences, selecting a single, representative one can be conducted differently. We review several procedures for this purpose, aiming to identify the most discriminant, average, central, benevolent, aggressive, parsimonious, or robust models. Also, we present three novel procedures that implement the robust assignment rule in practice. They exploit stochastic acceptabilities and maximize the support given to the resulting assignments by all feasible sorting models. The performance of sixteen procedures is verified on problem instances with different complexities. The results of an experimental study indicate the most efficient procedure in terms of classification accuracy, reproducing the DM's model, and delivering the most robust assignments. These include approaches identifying differently interpreted centers of the feasible polyhedron and robust methods introduced in this paper. Moreover, we discuss how the performance of all procedures is affected by different numbers of classes, criteria, characteristic points, and reference assignments. Finally, we illustrate the use of all approaches in a study concerning the assessment of the green performance of European cities.