India has a rich linguistic landscape with languages from 4 major language families spoken by over a billion people. 22 of these languages are listed in the Constitution of India (referred to as scheduled languages) are the focus of this work. Given the linguistic diversity, high-quality and accessible Machine Translation (MT) systems are essential in a country like India. Prior to this work, there was (i) no parallel training data spanning all 22 languages, (ii) no robust benchmarks covering all these languages and containing content relevant to India, and (iii) no existing translation models which support all the 22 scheduled languages of India. In this work, we aim to address this gap by focusing on the missing pieces required for enabling wide, easy, and open access to good machine translation systems for all 22 scheduled Indian languages. We identify four key areas of improvement: curating and creating larger training datasets, creating diverse and high-quality benchmarks, training multilingual models, and releasing models with open access. Our first contribution is the release of the Bharat Parallel Corpus Collection (BPCC), the largest publicly available parallel corpora for Indic languages. BPCC contains a total of 230M bitext pairs, of which a total of 126M were newly added, including 644K manually translated sentence pairs created as part of this work. Our second contribution is the release of the first n-way parallel benchmark covering all 22 Indian languages, featuring diverse domains, Indian-origin content, and source-original test sets. Next, we present IndicTrans2, the first model to support all 22 languages, surpassing existing models on multiple existing and new benchmarks created as a part of this work. Lastly, to promote accessibility and collaboration, we release our models and associated data with permissive licenses at https://github.com/AI4Bharat/IndicTrans2.

Declarative process specifications define the behavior of processes by means of rules based on Linear Temporal Logic on Finite Traces (LTLf). In a mining context, these specifications are inferred from, and checked on, multi-sets of runs recorded by information systems (namely, event logs). To this end, being able to gauge the degree to which process data comply with a specification is key. However, existing mining and verification techniques analyze the rules in isolation, thereby disregarding their interplay. In this paper, we introduce a framework to devise probabilistic measures for declarative process specifications. Thereupon, we propose a technique that measures the degree of satisfaction of specifications over event logs. To assess our approach, we conduct an evaluation with real-world data, evidencing its applicability in discovery, checking, and drift detection contexts.

Accurate uncertainty quantification is necessary to enhance the reliability of deep learning models in real-world applications. In the case of regression tasks, prediction intervals (PIs) should be provided along with the deterministic predictions of deep learning models. Such PIs are useful or "high-quality" as long as they are sufficiently narrow and capture most of the probability density. In this paper, we present a method to learn prediction intervals for regression-based neural networks automatically in addition to the conventional target predictions. In particular, we train two companion neural networks: one that uses one output, the target estimate, and another that uses two outputs, the upper and lower bounds of the corresponding PI. Our main contribution is the design of a novel loss function for the PI-generation network that takes into account the output of the target-estimation network and has two optimization objectives: minimizing the mean prediction interval width and ensuring the PI integrity using constraints that maximize the prediction interval probability coverage implicitly. Furthermore, we introduce a self-adaptive coefficient that balances both objectives within the loss function, which alleviates the task of fine-tuning. Experiments using a synthetic dataset, eight benchmark datasets, and a real-world crop yield prediction dataset showed that our method was able to maintain a nominal probability coverage and produce significantly narrower PIs without detriment to its target estimation accuracy when compared to those PIs generated by three state-of-the-art neural-network-based methods. In other words, our method was shown to produce higher-quality PIs.

Graph neural networks (GNN) are increasingly used to classify EEG for tasks such as emotion recognition, motor imagery and neurological diseases and disorders. A wide range of methods have been proposed to design GNN-based classifiers. Therefore, there is a need for a systematic review and categorisation of these approaches. We exhaustively search the published literature on this topic and derive several categories for comparison. These categories highlight the similarities and differences among the methods. The results suggest a prevalence of spectral graph convolutional layers over spatial. Additionally, we identify standard forms of node features, with the most popular being the raw EEG signal and differential entropy. Our results summarise the emerging trends in GNN-based approaches for EEG classification. Finally, we discuss several promising research directions, such as exploring the potential of transfer learning methods and appropriate modelling of cross-frequency interactions.

Through this paper, we introduce a novel driver cognitive load assessment dataset, CL-Drive, which contains Electroencephalogram (EEG) signals along with other physiological signals such as Electrocardiography (ECG) and Electrodermal Activity (EDA) as well as eye tracking data. The data was collected from 21 subjects while driving in an immersive vehicle simulator, in various driving conditions, to induce different levels of cognitive load in the subjects. The tasks consisted of 9 complexity levels for 3 minutes each. Each driver reported their subjective cognitive load every 10 seconds throughout the experiment. The dataset contains the subjective cognitive load recorded as ground truth. In this paper, we also provide benchmark classification results for different machine learning and deep learning models for both binary and ternary label distributions. We followed 2 evaluation criteria namely 10-fold and leave-one-subject-out (LOSO). We have trained our models on both hand-crafted features as well as on raw data.

We tackle the problem of sampling from intractable high-dimensional density functions, a fundamental task that often appears in machine learning and statistics. We extend recent sampling-based approaches that leverage controlled stochastic processes to model approximate samples from these target densities. The main drawback of these approaches is that the training objective requires full trajectories to compute, resulting in sluggish credit assignment issues due to use of entire trajectories and a learning signal present only at the terminal time. In this work, we present Diffusion Generative Flow Samplers (DGFS), a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments, via parameterizing an additional "flow function". Our method takes inspiration from the theory developed for generative flow networks (GFlowNets), allowing us to make use of intermediate learning signals. Through various challenging experiments, we demonstrate that DGFS achieves more accurate estimates of the normalization constant than closely-related prior methods.

We investigate unbiased high-dimensional mean estimators in differential privacy. We consider differentially private mechanisms whose expected output equals the mean of the input dataset, for every dataset drawn from a fixed bounded $d$-dimensional domain $K$. A classical approach to private mean estimation is to compute the true mean and add unbiased, but possibly correlated, Gaussian noise to it. In the first part of this paper, we study the optimal error achievable by a Gaussian noise mechanism for a given domain $K$ when the error is measured in the $\ell_p$ norm for some $p \ge 2$. We give algorithms that compute the optimal covariance for the Gaussian noise for a given $K$ under suitable assumptions, and prove a number of nice geometric properties of the optimal error. These results generalize the theory of factorization mechanisms from domains $K$ that are symmetric and finite (or, equivalently, symmetric polytopes) to arbitrary bounded domains. In the second part of the paper we show that Gaussian noise mechanisms achieve nearly optimal error among all private unbiased mean estimation mechanisms in a very strong sense. In particular, for every input dataset, an unbiased mean estimator satisfying concentrated differential privacy introduces approximately at least as much error as the best Gaussian noise mechanism. We extend this result to local differential privacy, and to approximate differential privacy, but for the latter the error lower bound holds either for a dataset or for a neighboring dataset, and this relaxation is necessary.

We describe the project REE-HDSC and outline our efforts to improve the quality of named entities extracted automatically from texts generated by hand-written text recognition (HTR) software. We describe a six-step processing pipeline and test it by processing 19th and 20th century death certificates from the civil registry of Curacao. We find that the pipeline extracts dates with high precision but that the precision of person name extraction is low. Next we show how name precision extraction can be improved by retraining HTR models with names, post-processing and by identifying and removing incorrect names.

Recently decades have witnessed the empirical success of framing Knowledge Graph (KG) embeddings via language models. However, language model-based KG embeddings are usually deployed as static artifacts, making them difficult to modify post-deployment without re-training after deployment. To address this issue, we propose a new task of editing language model-based KG embeddings in this paper. This task is designed to facilitate rapid, data-efficient updates to KG embeddings without compromising the performance of other aspects. We build four new datasets: E-FB15k237, A-FB15k237, E-WN18RR, and A-WN18RR, and evaluate several knowledge editing baselines demonstrating the limited ability of previous models to handle the proposed challenging task. We further propose a simple yet strong baseline dubbed KGEditor, which utilizes additional parametric layers of the hypernetwork to edit/add facts. Our comprehensive experimental results reveal that KGEditor excels in updating specific facts without impacting the overall performance, even when faced with limited training resources. Code and datasets are available in https://github.com/zjunlp/PromptKG/tree/main/deltaKG.

Context: Technical debt (TD) is a well-known metaphor for the long-term effects of architectural decisions in software development and the trade-off between producing high-quality, effective, and efficient code and meeting a release schedule. Thus, the code degrades and needs refactoring. A lack of resources, time, knowledge, or experience on the development team might cause TD in any software development project. Objective: In the context of TD detection, NLP has been utilized to identify the presence of TD automatically and even recognize specific types of TD. However, the enormous variety of feature extraction approaches and ML/DL algorithms employed in the literature often hinders researchers from trying to improve their performance. Method: In light of this, this SLR proposes a taxonomy of feature extraction techniques and algorithms used in technical debt detection: its objective is to compare and benchmark their performance in the examined studies. Results: We selected 55 articles that passed the quality evaluation of this SLR. We then investigated which feature extractions and algorithms were employed to identify TD in each SDLC phase. All approaches proposed in the analyzed studies were grouped into NLP, NLP+ML, and NLP+DL. This allows us to discuss the performance in three different ways. Conclusion: Overall, the NLP+DL group consistently outperforms in precision and F1-score for all projects, and in all but one project for the recall metric. Regarding the feature extraction techniques, the PTWE consistently achieves higher precision, recall, and F1-score for each project analyzed. Furthermore, TD types have been mapped, when possible, to SDLC phases: this served to determine the best-performing feature extractions and algorithms for each SDLC phase. Finally, based on the SLR results, we also identify implications that could be of concern to researchers and practitioners.