Large-scale transformer-based language models (LMs) demonstrate impressive capabilities in open text generation. However, controlling the generated text's properties such as the topic, style, and sentiment is challenging and often requires significant changes to the model architecture or retraining and fine-tuning the model on new supervised data. This paper presents a novel approach for Topical Language Generation (TLG) by combining a pre-trained LM with topic modeling information. We cast the problem using Bayesian probability formulation with topic probabilities as a prior, LM probabilities as the likelihood, and topical language generation probability as the posterior. In learning the model, we derive the topic probability distribution from the user-provided document's natural structure. Furthermore, we extend our model by introducing new parameters and functions to influence the quantity of the topical features presented in the generated text. This feature would allow us to easily control the topical properties of the generated text. Our experimental results demonstrate that our model outperforms the state-of-the-art results on coherency, diversity, and fluency while being faster in decoding.

In NLP, text classification is one of the primary problems we try to solve and its uses in language analyses are indisputable. The lack of labeled training data made it harder to do these tasks in low resource languages like Amharic. The task of collecting, labeling, annotating, and making valuable this kind of data will encourage junior researchers, schools, and machine learning practitioners to implement existing classification models in their language. In this short paper, we aim to introduce the Amharic text classification dataset that consists of more than 50k news articles that were categorized into 6 classes. This dataset is made available with easy baseline performances to encourage studies and better performance experiments.

Model predictive control is an advanced control approach for multivariable systems with constraints, which is reliant on an accurate dynamic model. Most real dynamic models are however affected by uncertainties, which can lead to closed-loop performance deterioration and constraint violations. In this paper we introduce a new algorithm to explicitly consider time-invariant stochastic uncertainties in optimal control problems. The difficulty of propagating stochastic variables through nonlinear functions is dealt with by combining Gaussian processes with polynomial chaos expansions. The main novelty in this paper is to use this combination in an efficient fashion to obtain mean and variance estimates of nonlinear transformations. Using this algorithm, it is shown how to formulate both chance-constraints and a probabilistic objective for the optimal control problem. On a batch reactor case study we firstly verify the ability of the new approach to accurately approximate the probability distributions required. Secondly, a tractable stochastic nonlinear model predictive control approach is formulated with an economic objective to demonstrate the closed-loop performance of the method via Monte Carlo simulations.

Off-policy evaluation (OPE) is the task of estimating the expected reward of a given policy based on offline data previously collected under different policies. Therefore, OPE is a key step in applying reinforcement learning to real-world domains such as medical treatment, where interactive data collection is expensive or even unsafe. As the observed data tends to be noisy and limited, it is essential to provide rigorous uncertainty quantification, not just a point estimation, when applying OPE to make high stakes decisions. This work considers the problem of constructing non-asymptotic confidence intervals in infinite-horizon off-policy evaluation, which remains a challenging open question. We develop a practical algorithm through a primal-dual optimization-based approach, which leverages the kernel Bellman loss (KBL) of Feng et al.(2019) and a new martingale concentration inequality of KBL applicable to time-dependent data with unknown mixing conditions. Our algorithm makes minimum assumptions on the data and the function class of the Q-function, and works for the behavior-agnostic settings where the data is collected under a mix of arbitrary unknown behavior policies. We present empirical results that clearly demonstrate the advantages of our approach over existing methods.

We introduce active testing: a new framework for sample-efficient model evaluation. While approaches like active learning reduce the number of labels needed for model training, existing literature largely ignores the cost of labeling test data, typically unrealistically assuming large test sets for model evaluation. This creates a disconnect to real applications where test labels are important and just as expensive, e.g. for optimizing hyperparameters. Active testing addresses this by carefully selecting the test points to label, ensuring model evaluation is sample-efficient. To this end, we derive theoretically-grounded and intuitive acquisition strategies that are specifically tailored to the goals of active testing, noting these are distinct to those of active learning. Actively selecting labels introduces a bias; we show how to remove that bias while reducing the variance of the estimator at the same time. Active testing is easy to implement, effective, and can be applied to any supervised machine learning method. We demonstrate this on models including WideResNet and Gaussian processes on datasets including CIFAR-100.

The Hawkes model is a point process observed on the real line, which generally corresponds to the time, where any previously encountered event has a direct influence on the chances of future events occurring. This past-dependent mathematical model was introduced in [1] and its first application was to model earthquakes occurrences [2, 3]. Since then, Hawkes processes have been widely used in various fields, for instance finance [4], social media [5, 6], epidemiology [7], sociology [8] and neuroscience [9]. The main advantage of Hawkes processes is their ability to model different kinds of relationships between phenomena through an unknown kernel or transfer function. The Hawkes model was originally introduced as a self-exciting point process where the appearance of an event increases the chances of another one triggering. Several estimation procedures have been proposed for the kernel function, both in parametric [2, 10, 11] and nonparametric [9, 12] frameworks. However, the inhibition setting, where the presence of an event decreases the chance of another occurring, has drawn less attention in the literature, although it can be of great interest in several fields, in particular in neuroscience [13]. In this inhibition context, the cluster representation [14] on which is based the construction of a self-exciting Hawkes process, is no longer valid.

This paper describes the submissions by team HWR to the Dravidian Language Identification (DLI) shared task organized at VarDial 2021 workshop. The DLI training set includes 16,674 YouTube comments written in Roman script containing code-mixed text with English and one of the three South Dravidian languages: Kannada, Malayalam, and Tamil. We submitted results generated using two models, a Naive Bayes classifier with adaptive language models, which has shown to obtain competitive performance in many language and dialect identification tasks, and a transformer-based model which is widely regarded as the state-of-the-art in a number of NLP tasks. Our first submission was sent in the closed submission track using only the training set provided by the shared task organisers, whereas the second submission is considered to be open as it used a pretrained model trained with external data. Our team attained shared second position in the shared task with the submission based on Naive Bayes. Our results reinforce the idea that deep learning methods are not as competitive in language identification related tasks as they are in many other text classification tasks.

Monte Carlo Tree Search (MCTS) is a decision-making algorithm that consists in searching large combinatorial spaces represented by trees. In such trees, nodes denote states, also referred to as configurations of the problem, whereas edges denote transitions (actions) from one state to another. MCTS has been originally proposed in the work by Kocsis and Szepesvári (2006) and by Coulom (2006), as an algorithm for making computer players in Go. It was quickly called a major breakthrough (Gelly et al., 2012) as it allowed for a leap from 14 kyu, which is an average amateur level, to 5 dan, which is considered an advanced level but not professional yet. Before MCTS, bots for combinatorial games had been using various modifications of the min-max alpha-beta pruning algorithm (Junghanns, 1998) such as MTD(f) (Plaat, 2014) and hand-crafted heuristics. In contrast to them, MCTS algorithm is at its core aheuristic, which means that no additional knowledge is required other than just rules of a game (or a problem, generally speaking). However, it is possible to take advantage of heuristics and include them in the MCTS approach to make it more efficient and improve its convergence. Moreover, the given problem often tends to be so complex, from the combinatorial point of view, that some form of external help, e.g.

In supervised machine learning, you usually have an input X, which goes into your prediction function to get your Y . You can then compare your prediction with the true value Y. This gives you your cost which you use to update the parameters θ. Sentiment analysis (also known as opinion mining or emotion AI) refers to the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. So, let's start sentiment analysis using Logistic Regression We will be using the sample twitter data set for this exercise.

The Panel Vector Autoregressive (PVAR) model is a popular tool for macroeconomic forecasting and structural analysis in multi-country applications since it allows for spillovers between countries in a very flexible fashion. However, this flexibility means that the number of parameters to be estimated can be enormous leading to over-parameterization concerns. Bayesian global-local shrinkage priors, such as the Horseshoe prior used in this paper, can overcome these concerns, but they require the use of Markov Chain Monte Carlo (MCMC) methods rendering them computationally infeasible in high dimensions. In this paper, we develop computationally efficient Bayesian methods for estimating PVARs using an integrated rotated Gaussian approximation (IRGA). This exploits the fact that whereas own country information is often important in PVARs, information on other countries is often unimportant. Using an IRGA, we split the the posterior into two parts: one involving own country coefficients, the other involving other country coefficients. Fast methods such as approximate message passing or variational Bayes can be used on the latter and, conditional on these, the former are estimated with precision using MCMC methods. In a forecasting exercise involving PVARs with up to $18$ variables for each of $38$ countries, we demonstrate that our methods produce good forecasts quickly.