Large-scale conversational assistants like Alexa, Siri, Cortana and Google Assistant process every utterance using multiple models for domain, intent and named entity recognition. Given the decoupled nature of model development and large traffic volumes, it is extremely difficult to identify utterances processed erroneously by such systems. We address this challenge to detect domain classification errors using offline Transformer models. We combine utterance encodings from a RoBERTa model with the Nbest hypothesis produced by the production system. We then fine-tune end-to-end in a multitask setting using a small dataset of humanannotated utterances with domain classification errors. We tested our approach for detecting misclassifications from one domain that accounts for <0.5% of the traffic in a large-scale conversational AI system. Our approach achieves an F1 score of 30% outperforming a bi- LSTM baseline by 16.9% and a standalone RoBERTa model by 4.8%. We improve this further by 2.2% to 32.2% by ensembling multiple models.

Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource target languages, the augmented data sets are often noisy, and thus impede the performance of SLU models. In this paper we focus on mitigating noise in augmented data. We develop a denoising training approach. Multiple models are trained with data produced by various augmented methods. Those models provide supervision signals to each other. The experimental results show that our method outperforms the existing state of the art by 3.05 and 4.24 percentage points on two benchmark datasets, respectively. The code will be made open sourced on github.

In this paper, we address the "black-box" problem in predictive process analytics by building interpretable models that are capable to inform both what and why is a prediction. Predictive process analytics is a newly emerged discipline dedicated to providing business process intelligence in modern organisations. It uses event logs, which capture process execution traces in the form of multi-dimensional sequence data, as the key input to train predictive models. These predictive models, often built upon deep learning techniques, can be used to make predictions about the future states of business process execution. We apply attention mechanism to achieve model interpretability. We propose i) two types of attentions: event attention to capture the impact of specific process events on a prediction, and attribute attention to reveal which attribute(s) of an event influenced the prediction; and ii) two attention mechanisms: shared attention mechanism and specialised attention mechanism to reflect different design decisions in when to construct attribute attention on individual input features (specialised) or using the concatenated feature tensor of all input feature vectors (shared). These lead to two distinct attention-based models, and both are interpretable models that incorporate interpretability directly into the structure of a process predictive model. We conduct experimental evaluation of the proposed models using real-life dataset, and comparative analysis between the models for accuracy and interpretability, and draw insights from the evaluation and analysis results.

TORONTO and LONDON, Aug. 20, 2021 (GLOBE NEWSWIRE) -- ACCA (the Association of Chartered Certified Accountants) and Chartered Accountants Australia and New Zealand (CA ANZ) reveal in a new report the pressing need for the accountancy profession to make the necessary connections between Artificial Intelligence (AI) and its relationship to environmental, social and governance (ESG) dimensions. Polling over 5,700 respondents globally, including an expert panel of ACCA members across North America, the research reveals a cautious tone, with fewer than half (43%) believing that the impact of AI on their rights as an individual is positive – such as safety and personal security, levels of fairness, levels of choice, levels of transparency. In North America, 30% of respondents believe this to be the case. ACCA and CA ANZ say in Ethics for sustainable AI adoption: Connecting AI and ESG that accountants, with their explicit and long-standing commitment to ethical practices, are well placed to guide organizations along a responsible path for AI adoption. Jillian Couse, Head of ACCA North America says: 'Our findings present a wake-up call for the accountancy profession to lead the way and become the super connectors needed to ensure an ethical approach.

FURA Gems has announced a partnership with India-based Cognecto to improve operational efficiency, sustainability, productivity and decrease the carbon footprint of its Australian mining operation. Cognecto, which calls itself India's leading artificial intelligence-based heavy equipment monitoring company, has deployed an integrated custom-built hardware sensor and remote telemetry data protocol for FURA to share the data from its Sapphire mining operations in Queensland to company headquarters in Dubai. This collaborative effort forges a solution combining heavy equipment monitoring and analytics to empower operational visibility and control wherever and whenever, according to Cognecto. In addition, FURA employees can access real-time fleet updates via a "well-integrated, easy-to-implement, and zero-tech footprint AI platform created by Cognecto to improve operational conditions and enhances safety", it said. Operational insights for real-time tracking are delivered using a web interface, while the alerts can be relayed on any commonly used messaging platform.

Graph feature extraction is a fundamental task in graphs analytics. Using feature vectors (graph descriptors) in tandem with data mining algorithms that operate on Euclidean data, one can solve problems such as classification, clustering, and anomaly detection on graph-structured data. This idea has proved fruitful in the past, with spectral-based graph descriptors providing state-of-the-art classification accuracy on benchmark datasets. However, these algorithms do not scale to large graphs since: 1) they require storing the entire graph in memory, and 2) the end-user has no control over the algorithm's runtime. In this paper, we present single-pass streaming algorithms to approximate structural features of graphs (counts of subgraphs of order $k \geq 4$). Operating on edge streams allows us to avoid keeping the entire graph in memory, and controlling the sample size enables us to control the time taken by the algorithm. We demonstrate the efficacy of our descriptors by analyzing the approximation error, classification accuracy, and scalability to massive graphs. Our experiments showcase the effect of the sample size on approximation error and predictive accuracy. The proposed descriptors are applicable on graphs with millions of edges within minutes and outperform the state-of-the-art descriptors in classification accuracy.

The following defines intent, an arbitrary task and its solutions, and then argues that an agent which always constructs what is called an Intensional Solution would qualify as artificial general intelligence. We then explain how natural language may emerge and be acquired by such an agent, conferring the ability to model the intent of other individuals labouring under similar compulsions, because an abstract symbol system and the solution to a task are one and the same.

More predictable words are easier to process - they are read faster and elicit smaller neural signals associated with processing difficulty, most notably, the N400 component of the event-related brain potential. Thus, it has been argued that prediction of upcoming words is a key component of language comprehension, and that studying the amplitude of the N400 is a valuable way to investigate the predictions that we make. In this study, we investigate whether the linguistic predictions of computational language models or humans better reflect the way in which natural language stimuli modulate the amplitude of the N400. One important difference in the linguistic predictions of humans versus computational language models is that while language models base their predictions exclusively on the preceding linguistic context, humans may rely on other factors. We find that the predictions of three top-of-the-line contemporary language models - GPT-3, RoBERTa, and ALBERT - match the N400 more closely than human predictions. This suggests that the predictive processes underlying the N400 may be more sensitive to the surface-level statistics of language than previously thought.

Multi-agent inverse reinforcement learning (MIRL) can be used to learn reward functions from agents in social environments. To model realistic social dynamics, MIRL methods must account for suboptimal human reasoning and behavior. Traditional formalisms of game theory provide computationally tractable behavioral models, but assume agents have unrealistic cognitive capabilities. This research identifies and compares mechanisms in MIRL methods which a) handle noise, biases and heuristics in agent decision making and b) model realistic equilibrium solution concepts. MIRL research is systematically reviewed to identify solutions for these challenges. The methods and results of these studies are analyzed and compared based on factors including performance accuracy, efficiency, and descriptive quality. We found that the primary methods for handling noise, biases and heuristics in MIRL were extensions of Maximum Entropy (MaxEnt) IRL to multi-agent settings. We also found that many successful solution concepts are generalizations of the traditional Nash Equilibrium (NE). These solutions include the correlated equilibrium, logistic stochastic best response equilibrium and entropy regularized mean field NE. Methods which use recursive reasoning or updating also perform well, including the feedback NE and archive multi-agent adversarial IRL. Success in modeling specific biases and heuristics in single-agent IRL and promising results using a Theory of Mind approach in MIRL imply that modeling specific biases and heuristics may be useful. Flexibility and unbiased inference in the identified alternative solution concepts suggest that a solution concept which has both recursive and generalized characteristics may perform well at modeling realistic social interactions.

Recent work on Open Domain Question Answering has shown that there is a large discrepancy in model performance between novel test questions and those that largely overlap with training questions. However, it is as of yet unclear which aspects of novel questions that make them challenging. Drawing upon studies on systematic generalization, we introduce and annotate questions according to three categories that measure different levels and kinds of generalization: training set overlap, compositional generalization (comp-gen), and novel entity generalization (novel-entity). When evaluating six popular parametric and non-parametric models, we find that for the established Natural Questions and TriviaQA datasets, even the strongest model performance for comp-gen/novel-entity is 13.1/5.4% and 9.6/1.5% lower compared to that for the full test set -- indicating the challenge posed by these types of questions. Furthermore, we show that whilst non-parametric models can handle questions containing novel entities, they struggle with those requiring compositional generalization. Through thorough analysis we find that key question difficulty factors are: cascading errors from the retrieval component, frequency of question pattern, and frequency of the entity.