While human evaluation remains best practice for accurately judging the faithfulness of automatically-generated summaries, few solutions exist to address the increased difficulty and workload when evaluating long-form summaries. Through a survey of 162 papers on long-form summarization, we first shed light on current human evaluation practices surrounding long-form summaries. We find that 73% of these papers do not perform any human evaluation on model-generated summaries, while other works face new difficulties that manifest when dealing with long documents (e.g., low inter-annotator agreement). Motivated by our survey, we present LongEval, a set of guidelines for human evaluation of faithfulness in long-form summaries that addresses the following challenges: (1) How can we achieve high inter-annotator agreement on faithfulness scores? (2) How can we minimize annotator workload while maintaining accurate faithfulness scores? and (3) Do humans benefit from automated alignment between summary and source snippets? We deploy LongEval in annotation studies on two long-form summarization datasets in different domains (SQuALITY and PubMed), and we find that switching to a finer granularity of judgment (e.g., clause-level) reduces inter-annotator variance in faithfulness scores (e.g., std-dev from 18.5 to 6.8). We also show that scores from a partial annotation of fine-grained units highly correlates with scores from a full annotation workload (0.89 Kendall's tau using 50% judgments). We release our human judgments, annotation templates, and our software as a Python library for future research.

Graphs are a powerful data structure to represent relational data and are widely used to describe complex real-world data structures. Probabilistic Graphical Models (PGMs) have been well-developed in the past years to mathematically model real-world scenarios in compact graphical representations of distributions of variables. Graph Neural Networks (GNNs) are new inference methods developed in recent years and are attracting growing attention due to their effectiveness and flexibility in solving inference and learning problems over graph-structured data. These two powerful approaches have different advantages in capturing relations from observations and how they conduct message passing, and they can benefit each other in various tasks. In this survey, we broadly study the intersection of GNNs and PGMs. Specifically, we first discuss how GNNs can benefit from learning structured representations in PGMs, generate explainable predictions by PGMs, and how PGMs can infer object relationships. Then we discuss how GNNs are implemented in PGMs for more efficient inference and structure learning. In the end, we summarize the benchmark datasets used in recent studies and discuss promising future directions.

Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and generating pseudo-labels (PLs) with it, here PLs are generated in end-to-end manner as training proceeds, improving training speed and the accuracy of the final model. PL shares a common theme with teacher-student models such as distillation in that a teacher model generates targets that need to be mimicked by the student model being trained. However, interestingly, PL strategies in general use hard-labels, whereas distillation uses the distribution over labels as the target to mimic. Inspired by distillation we expect that specifying the whole distribution (aka soft-labels) over sequences as the target for unlabeled data, instead of a single best pass pseudo-labeled transcript (hard-labels) should improve PL performance and convergence. Surprisingly and unexpectedly, we find that soft-labels targets can lead to training divergence, with the model collapsing to a degenerate token distribution per frame. We hypothesize that the reason this does not happen with hard-labels is that training loss on hard-labels imposes sequence-level consistency that keeps the model from collapsing to the degenerate solution. In this paper, we show several experiments that support this hypothesis, and experiment with several regularization approaches that can ameliorate the degenerate collapse when using soft-labels. These approaches can bring the accuracy of soft-labels closer to that of hard-labels, and while they are unable to outperform them yet, they serve as a useful framework for further improvements.

Machine learning (ML) compilers are an active area of research because they offer the potential to automatically speedup tensor programs. Kernel fusion is often cited as an important optimization performed by ML compilers. However, there exists a knowledge gap about how XLA, the most common ML compiler, applies this nuanced optimization, what kind of speedup it can afford, and what low-level effects it has on hardware. Our paper aims to bridge this knowledge gap by studying key compiler passes of XLA's source code. Our evaluation on a reinforcement learning environment Cartpole shows how different fusion decisions in XLA are made in practice. Furthermore, we implement several XLA kernel fusion strategies that can achieve up to 10.56x speedup compared to our baseline implementation.

High dimensional data for classification does create many difficulties for machine learning algorithms. The generalization can be done using ensemble learning methods such as bagging based supervised non-parametric random forest algorithm. In this paper we solve the problem of binary classification for high dimensional data using random forest for polycystic ovary syndrome dataset. We have performed the implementation and provided a detailed visualization of the data for general inference. The training accuracy that we have achieved is 95.6% and validation accuracy over 91.74% respectively.

Water consumption remains a major concern among the world's future challenges. For applications like load monitoring and demand response, deep learning models are trained using enormous volumes of consumption data in smart cities. On the one hand, the information used is private. For instance, the precise information gathered by a smart meter that is a part of the system's IoT architecture at a consumer's residence may give details about the appliances and, consequently, the consumer's behavior at home. On the other hand, enormous data volumes with sufficient variation are needed for the deep learning models to be trained properly. This paper introduces a novel model for water consumption prediction in smart cities while preserving privacy regarding monthly consumption. The proposed approach leverages federated learning (FL) as a machine learning paradigm designed to train a machine learning model in a distributed manner while avoiding sharing the users data with a central training facility. In addition, this approach is promising to reduce the overhead utilization through decreasing the frequency of data transmission between the users and the central entity. Extensive simulation illustrate that the proposed approach shows an enhancement in predicting water consumption for different households.

Become a high qualified data scientist by taking these 10 best data science courses on Udemy. Learn how to use NumPy, Pandas, Seaborn, Matplotlib, Plotly, Scikit-Learn, Machine Learning, Tensorflow, and more! Created by Lazy Programmer Inc. Learn how to apply probability and statistics to real data science and business applications! Created by Lazy Programmer Inc. Today, I spend most of my time as an artificial intelligence and machine learning engineer with a focus on deep learning, although I have also been known as a data scientist, big data engineer, and full stack software engineer.

I have published numerous articles on AI and related topics and am committed to staying up-to-date on the latest research and advancements in the field.

Hello World is a weekly newsletter--delivered every Saturday morning--that goes deep into our original reporting and the questions we put to big thinkers in the field. If you have been reading all the hype about the latest artificial intelligence chatbot, ChatGPT, you might be excused for thinking that the end of the world is nigh. The clever AI chat program has captured the imagination of the public for its ability to generate poems and essays instantaneously, its ability to mimic different writing styles, and its ability to pass some law and business school exams. Teachers are worried students will use it to cheat in class (New York City public schools have already banned it). Writers are worried it will take their jobs (BuzzFeed and CNET have already started using AI to create content).

Is the end of homework near? As new powerful artificial intelligence (AI) tools like ChatGPT take the Internet by storm, teachers concerned with AI-driven cheating are questioning their teaching and assessment methods. ChatGPT, the most powerful AI language model ever developed by the company OpenAI, is capable of generating natural-sounding text on demand, including in a specific style or in several languages, in just a few seconds. The quality of the copy it produces is sufficient to impress teachers in secondary and higher education, and even researchers. "Young or not, we are all amazed at how quickly and relevantly it responds," Cécile Cathelin, a teacher at a high school in the French city of Tours, told Euronews Next.