Actionable sentences are terms that, in the most basic sense, imply the necessity of taking a specific action. In Linguistic terms, they are steps to achieve an operation, often through the usage of action verbs. For example, the sentence, `Get your homework finished by tomorrow` qualifies as actionable since it demands a specific action (In this case, finishing homework) to be taken. In contrast, a simple sentence such as, `I like to play the guitar` does not qualify as an actionable phrase since it simply states a personal choice of the person instead of demanding a task to be finished. In this paper, the aim is to explore if Actionables can be extracted from raw text using Linguistic filters designed from scratch. These filters are specially catered to identifying actionable text using Transfer Learning as the lead role. Actionable Detection can be used in detecting emergency tasks during a crisis, Instruction accuracy for First aid and can also be used to make productivity tools like automatic ToDo list generators from conferences. To accomplish this, we use the Enron Email Dataset and apply our Linguistic filters on the cleaned textual data. We then use Transfer Learning with the Universal Sentence Encoder to train a model to classify whether a given string of raw text is actionable or not.

We propose the first character-level white-box adversarial attack method against transformer models. The intuition of our method comes from the observation that words are split into subtokens before being fed into the transformer models and the substitution between two close subtokens has a similar effect to the character modification. Our method mainly contains three steps. First, a gradient-based method is adopted to find the most vulnerable words in the sentence. Then we split the selected words into subtokens to replace the origin tokenization result from the transformer tokenizer. Finally, we utilize an adversarial loss to guide the substitution of attachable subtokens in which the Gumbel-softmax trick is introduced to ensure gradient propagation. Meanwhile, we introduce the visual and length constraint in the optimization process to achieve minimum character modifications. Extensive experiments on both sentence-level and token-level tasks demonstrate that our method could outperform the previous attack methods in terms of success rate and edit distance. Furthermore, human evaluation verifies our adversarial examples could preserve their origin labels.

Neural attention models have achieved significant improvements on many natural language processing tasks. However, the quadratic memory complexity of the self-attention module with respect to the input length hinders their applications in long text summarization. Instead of designing more efficient attention modules, we approach this problem by investigating if models with a restricted context can have competitive performance compared with the memory-efficient attention models that maintain a global context by treating the input as a single sequence. Our model is applied to individual pages which contain parts of inputs grouped by the principle of locality during both encoding and decoding. We empirically investigated three kinds of locality in text summarization at different levels of granularity, ranging from sentences to documents. Our experimental results show that our model has a better performance compared with strong baselines with efficient attention modules, and our analysis provides further insights into our locality-aware modeling strategy.

Neural Network (NN) models provide potential to speed up the drug discovery process and reduce its failure rates. The success of NN models require uncertainty quantification (UQ) as drug discovery explores chemical space beyond the training data distribution. Standard NN models do not provide uncertainty information. Methods that combine Bayesian models with NN models address this issue, but are difficult to implement and more expensive to train. Some methods require changing the NN architecture or training procedure, limiting the selection of NN models. Moreover, predictive uncertainty can come from different sources. It is important to have the ability to separately model different types of predictive uncertainty, as the model can take assorted actions depending on the source of uncertainty. In this paper, we examine UQ methods that estimate different sources of predictive uncertainty for NN models aiming at drug discovery. We use our prior knowledge on chemical compounds to design the experiments. By utilizing a visualization method we create non-overlapping and chemically diverse partitions from a collection of chemical compounds. These partitions are used as training and test set splits to explore NN model uncertainty. We demonstrate how the uncertainties estimated by the selected methods describe different sources of uncertainty under different partitions and featurization schemes and the relationship to prediction error.

Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and interpretable NLU systems. However, despite the many datasets and resources built as part of this effort, the majority have small-scale annotations and limited scope, which is insufficient to solve general decomposition tasks. In this paper, we look at large-scale intermediate pre-training of decomposition-based transformers using distant supervision from comparable texts, particularly large-scale parallel news. We show that with such intermediate pre-training, developing robust decomposition-based models for a diverse range of tasks becomes more feasible. For example, on semantic parsing, our model, DecompT5, improves 20% to 30% on two datasets, Overnight and TORQUE, over the baseline language model. We further use DecompT5 to build a novel decomposition-based QA system named DecompEntail, improving over state-of-the-art models, including GPT-3, on both HotpotQA and StrategyQA by 8% and 4%, respectively.

The U.K.'s privacy watchdog has warned against use of so-called "emotion analysis" technologies for anything more serious than kids' party games, saying there's a discrimination risk attached to applying "immature" biometric tech that makes pseudoscientific claims about being able to recognize people's emotions using AI to interpret biometric data inputs. Such AI systems'function', if we can use the word, by claiming to be able to'read the tea leaves' of one or more biometric signals, such as heart rate, eye movements, facial expression, skin moisture, gait tracking, vocal tone etc, and perform emotion detection or sentiment analysis to predict how the person is feeling -- presumably after being trained on a bunch of visual data of faces frowning, faces smiling etc (but you can immediately see the problem with trying to assign individual facial expressions to absolute emotional states -- because no two people, and often no two emotional states, are the same; hence hello pseudoscience!). The watchdog's deputy commissioner, Stephen Bonner, appears to agree that this high tech nonsense must be stopped -- saying today there's no evidence that such technologies do actually work as claimed (or that they will ever work). "Developments in the biometrics and emotion AI market are immature. They may not work yet, or indeed ever," he warned in a statement. "While there are opportunities present, the risks are currently greater.

Russia has suspended its participation in a landmark agreement that allowed vital grain exports from Ukraine after what it said was a drone attack on Russian ships in occupied Crimea. Russia's defence ministry said Ukraine attacked the Black Sea Fleet near Sevastopol in the annexed Crimean Peninsula with 16 drones in the early hours of Saturday, and that British navy "specialists" had helped coordinate the "terrorist" attack. London bluntly rejected Moscow's claim. The Turkey and UN-brokered deal to unlock grain exports signed between Russia and Ukraine in July is critical to easing the global food crisis caused by the conflict. The agreement has already allowed more than 9 million tonnes of Ukrainian grain to be exported and was due to be renewed on November 19.

Australian surf lifesavers are increasingly using drones to spot sharks at the beach before they get too close to swimmers. But just how reliable are they? Discerning whether that dark splodge in the water is a shark or just, say, seaweed isn't always straightforward and, in reasonable conditions, drone pilots generally make the right call only 60% of the time. While this has implications for public safety, it can also lead to unnecessary beach closures and public alarm. Engineers are trying to boost the accuracy of these shark-spotting drones with artificial intelligence (AI).

Fox News contributor Mike Pompeo joined'America Reports' to discuss Putin alleging Ukraine will use a'dirty bomb' in the war and the latest on Hunter Biden's business dealings. Russia announced it is withdrawing from the UN-facilitated Black Sea grain export agreement after an attack on its naval forces in Sevastopol, Crimea. "We've seen the reports from the Russian Federation regarding the suspension of their participation in the Black Sea Grain Initiative following an attack on the Russian Black Sea Fleet," Stéphane Dujarric, spokesman for the U.N. Secretary General, said in a press release Saturday morning. "We are in touch with the Russian authorities on this matter." "It is vital that all parties refrain from any action that would imperil the Black Sea Grain Initiative which is a critical humanitarian effort that is clearly having a positive impact on access to food for millions of people around the world," Dujarric added.

British navy personnel planted explosives and blew up the Nord Stream gas pipelines last month, Russia's defence ministry says, a claim London called false and designed to distract from Moscow's military failures in Ukraine. Russia did not give evidence for its allegation that a leading NATO member had sabotaged critical Russian infrastructure amid the worst crisis in relations between the West and Moscow since the depths of the Cold War. The Russian ministry alleged "British specialists" from the same unit that directed Ukrainian drone attacks on ships from the Russian Black Sea fleet in Crimea earlier on Saturday were responsible for the Nord Stream pipeline sabotage. "According to available information, representatives of this unit of the British Navy took part in the planning, provision and implementation of a terrorist attack in the Baltic Sea on September 26 this year – blowing up the Nord Stream 1 and Nord Stream 2 gas pipelines," the ministry said. The United Kingdom denied the accusation.