This manuscript describes the I4U submission to the 2020 NIST Speaker Recognition Evaluation (SRE'20) Conversational Telephone Speech (CTS) Challenge. The I4U's submission was resulted from active collaboration among researchers across eight research teams - I$^2$R (Singapore), UEF (Finland), VALPT (Italy, Spain), NEC (Japan), THUEE (China), LIA (France), NUS (Singapore), INRIA (France) and TJU (China). The submission was based on the fusion of top performing sub-systems and sub-fusion systems contributed by individual teams. Efforts have been spent on the use of common development and validation sets, submission schedule and milestone, minimizing inconsistency in trial list and score file format across sites.

We consider the task of weighted first-order model counting (WFOMC) used for probabilistic inference in the area of statistical relational learning. Given a formula $\phi$, domain size $n$ and a pair of weight functions, what is the weighted sum of all models of $\phi$ over a domain of size $n$? It was shown that computing WFOMC of any logical sentence with at most two logical variables can be done in time polynomial in $n$. However, it was also shown that the task is $\texttt{#}P_1$-complete once we add the third variable, which inspired the search for extensions of the two-variable fragment that would still permit a running time polynomial in $n$. One of such extension is the two-variable fragment with counting quantifiers. In this paper, we prove that adding a linear order axiom (which forces one of the predicates in $\phi$ to introduce a linear ordering of the domain elements in each model of $\phi$) on top of the counting quantifiers still permits a computation time polynomial in the domain size. We present a new dynamic programming-based algorithm which can compute WFOMC with linear order in time polynomial in $n$, thus proving our primary claim.

The graph represents a network of 2,085 Twitter users whose tweets in the requested range contained "#cloudcomputing", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Monday, 17 October 2022 at 15:12 UTC. The requested start date was Monday, 17 October 2022 at 00:01 UTC and the maximum number of days (going backward) was 14. The maximum number of tweets collected was 7,500. The tweets in the network were tweeted over the 2-day, 10-hour, 26-minute period from Friday, 14 October 2022 at 13:27 UTC to Sunday, 16 October 2022 at 23:53 UTC.

In a paper on'Artificial Intelligence in Nursing' presented jointly by Dr Ramesh M.Sc Phd, HoD Medical Surgical Nursing, St Paul's Hospital Millennium Medical College, Ethiopia, and Dr S. Indira, Dean of Narayana Nursing College, said AI offers three advantages over traditional methods -- the ability to quickly consider large volumes of data in risk prediction, increased intervention specificity (accurately flagging patients most at-risk) and automated adjustments in variable selection and calculation. "AI can help detect which patient features are most important in public health applications, allowing for more focused preventive interventions. "AI may more accurately predict fall risk without manual calculation and provide automatic warning systems," said Prof. Ramesh and Dr Indira. They have also highlighted the role of mobile health technologies (smartphones, smartphone apps, and wearable technologies) to help manage chronic illnesses by receiving and sending data directly between patients and care-providers, creating a comprehensive picture of the dynamic state of a patient's health in their everyday environments. According to the duo, sensor-based technologies, when placed in the home or hospital environment and used in combination, help nurses compose text and multimedia messages (for sharing photos and videos), measure body movement and collect weight, movement, and environmental (temperature, light, sound, air quality) data. In a paper on'Artificial Intelligence in Nursing' presented jointly by Dr Ramesh M.Sc Phd, HoD Medical Surgical Nursing, St Paul's Hospital Millennium Medical College, Ethiopia, and Dr S. Indira, Dean of Narayana Nursing College, said AI offers three advantages over traditional methods -- the ability to quickly consider large volumes of data in risk prediction, increased intervention specificity (accurately flagging patients most at-risk) and automated adjustments in variable selection and calculation. "AI can help detect which patient features are most important in public health applications, allowing for more focused preventive interventions.

We introduce the Block-Recurrent Transformer, which applies a transformer layer in a recurrent fashion along a sequence, and has linear complexity with respect to sequence length. Our recurrent cell operates on blocks of tokens rather than single tokens during training, and leverages parallel computation within a block in order to make efficient use of accelerator hardware. The cell itself is strikingly simple. It is merely a transformer layer: it uses self-attention and cross-attention to efficiently compute a recurrent function over a large set of state vectors and tokens. Our design was inspired in part by LSTM cells, and it uses LSTM-style gates, but it scales the typical LSTM cell up by several orders of magnitude. Our implementation of recurrence has the same cost in both computation time and parameter count as a conventional transformer layer, but offers dramatically improved perplexity in language modeling tasks over very long sequences. Our model out-performs a long-range Transformer XL baseline by a wide margin, while running twice as fast. We demonstrate its effectiveness on PG19 (books), arXiv papers, and GitHub source code. Our code has been released as open source.

Let two sequences of eventualities x (signifying the sequence, x0,x1, x2,...,xn-1) and y (signifying the sequence, y0, y1, y2,..,yn-1) both recur over the same time interval and it is required to determine whether or not a subinterval exists within the said interval which is a common subinterval of the intervals of occurrence of xp and yq. This paper presents two algorithms for solving the problem. the first explores an arbitrary cycle of the double recurrence for the existence of such an interval. its worst case running time is quadratic. The other algorithm is based on the novel notion of gcd-partitions and has a linear worst case running time. If the eventuality sequence pair (W,z) is a gcd-partition for the double recurrence (x, y),then, from a certain property of gcd-partitions, within any cycle of the double recurrence, there exists r and s such that intervals of occurrence of xp and yq are non-disjoint with the interval of co-occurrence of wr and zs. As such, a coincidence between xp and yq occurs within a cycle of the double recurrence if and only if such r and s exist so that the interval of co-occurrence of wr and zs shares a common interval with the common interval of occurrences of xp and yq. The algorithm systematically reduces the number of wr and zs pairs to be explored in the process of finding the existence of the coincidence.

Music composition, like most art forms, has for a long time been a skill specific to human beings. Music composition has an intuitive side to it necessary to determine which pitches create harmorny together, what chords can be played after a certain note, or what note progressions are in violation of intrinsic musical theory. With the recent successes in neural network modeling of predictive natural behaviour and generative models, there have been good applications of modelling note progression probabilities for music generation. The two dominant approaches to neural music generation are adversarial training Sutskever et al. [2014], Liu and Randall [2016], Yang et al. [2017], Dong et al. [2018], and sequence-to-sequence recurrent networks Chung et al. [2014], Waite [2016], Weel [2017], each with its merits. Although Wave-form representations have been shown to be a viable way to generate audio not necessarily specific to music Oord et al. [2016a], it is symbolic representations that are favoured in literature for the task of music generation Mogren [2016], Yang et al. [2017], Lerdahl and Jackendoff [1983], Colombo and Gerstner [2018], Chung et al. [2014]. Owing to the existing lack of out-right comparisons between adversarial and non-adversarial training for music generation, the aim of this study is to compare music samples generated by two generative models, one trained in an adversarial setting, and the other in a non adversarial setting, using musical instrument digital interface (MIDI) data.

Machine learning (ML) is becoming increasingly crucial in many fields of engineering but has not yet played out its full potential in bioprocess engineering. While experimentation has been accelerated by increasing levels of lab automation, experimental planning and data modeling are still largerly depend on human intervention. ML can be seen as a set of tools that contribute to the automation of the whole experimental cycle, including model building and practical planning, thus allowing human experts to focus on the more demanding and overarching cognitive tasks. First, probabilistic programming is used for the autonomous building of predictive models. Second, machine learning automatically assesses alternative decisions by planning experiments to test hypotheses and conducting investigations to gather informative data that focus on model selection based on the uncertainty of model predictions. This review provides a comprehensive overview of ML-based automation in bioprocess development. On the one hand, the biotech and bioengineering community should be aware of the potential and, most importantly, the limitation of existing ML solutions for their application in biotechnology and biopharma. On the other hand, it is essential to identify the missing links to enable the easy implementation of ML and Artificial Intelligence (AI) tools in valuable solutions for the bio-community.

Many recent named entity recognition (NER) studies criticize flat NER for its non-overlapping assumption, and switch to investigating nested NER. However, existing nested NER models heavily rely on training data annotated with nested entities, while labeling such data is costly. This study proposes a new subtask, nested-from-flat NER, which corresponds to a realistic application scenario: given data annotated with flat entities only, one may still desire the trained model capable of recognizing nested entities. To address this task, we train span-based models and deliberately ignore the spans nested inside labeled entities, since these spans are possibly unlabeled entities. With nested entities removed from the training data, our model achieves 54.8%, 54.2% and 41.1% F1 scores on the subset of spans within entities on ACE 2004, ACE 2005 and GENIA, respectively. This suggests the effectiveness of our approach and the feasibility of the task. In addition, the model's performance on flat entities is entirely unaffected. We further manually annotate the nested entities in the test set of CoNLL 2003, creating a nested-from-flat NER benchmark. Analysis results show that the main challenges stem from the data and annotation inconsistencies between the flat and nested entities.

A growing body of research has demonstrated the inability of NLP models to generalize compositionally and has tried to alleviate it through specialized architectures, training schemes, and data augmentation, among other approaches. In this work, we study a different approach: training on instances with diverse structures. We propose a model-agnostic algorithm for subsampling such sets of instances from a labeled instance pool with structured outputs. Evaluating on both compositional template splits and traditional IID splits of 5 semantic parsing datasets of varying complexity, we show that structurally diverse training using our algorithm leads to comparable or better generalization than prior algorithms in 9 out of 10 dataset-split type pairs. In general, we find structural diversity to consistently improve sample efficiency compared to random train sets. Moreover, we show that structurally diverse sampling yields comprehensive test sets that are a lot more challenging than IID test sets. Finally, we provide two explanations for improved generalization from diverse train sets: 1) improved coverage of output substructures, and 2) a reduction in spurious correlations between these substructures.