Related papers: Multi-label Classification for Automatic Tag Predi…

Multi-label classification (MLC) is an important class of machine learning problems that come with a wide spectrum of applications, each demanding a possibly different evaluation criterion. When solving the MLC problems, we generally expect…

Acquiring labelled training data remains a costly task in real world machine learning projects to meet quantity and quality requirements. Recently Large Language Models (LLMs), notably GPT-4, have shown great promises in labelling data with…

Deep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new concepts quickly is limited. Meta-learning is one approach to address this…

Many thousands of patent applications arrive at patent offices around the world every day. One important subtask when a patent application is submitted is to assign one or more classification codes from the complex and hierarchical patent…

Software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or identifying the defect-prone code changes. Considering that…

It has been found that stochastic algorithms often find good solutions much more rapidly than inherently-batch approaches. Indeed, a very useful rule of thumb is that often, when solving a machine learning problem, an iterative technique…

Optimization is ubiquitous in our daily lives. In the past, (sub-)optimal solutions to any problem have been derived by trial and error, sheer luck, or the expertise of knowledgeable individuals. In our contemporary age, there thankfully…

Much algorithmic research in NLP aims to efficiently manipulate rich formal structures. An algorithm designer typically seeks to provide guarantees about their proposed algorithm -- for example, that its running time or space complexity is…

Automated machine learning (AutoML) and deep learning (DL) are two cutting-edge paradigms used to solve a myriad of inductive learning tasks. In spite of their successes, little guidance exists for when to choose one approach over the other…

Static analysis is one of the most widely adopted techniques to find software bugs before code is put in production. Designing and implementing effective and efficient static analyses is difficult and requires high expertise, which results…

With the rise of social media like Twitter and of software distribution platforms like app stores, users got various ways to express their opinion about software products. Popular software vendors get user feedback thousandfold per day.…

Recently, Automated Machine Learning (AutoML) has registered increasing success with respect to tabular data. However, the question arises whether AutoML can also be applied effectively to text classification tasks. This work compares four…

Heterogeneous computing systems, which combine general-purpose processors with specialized accelerators, are increasingly important for optimizing the performance of modern applications. A central challenge is to decide which parts of an…

We present LTLS, a technique for multiclass and multilabel prediction that can perform training and inference in logarithmic time and space. LTLS embeds large classification problems into simple structured prediction problems and relies on…

IT helpdesks are charged with the task of responding quickly to user queries. To give the user confidence that their query matters, the helpdesk will auto-reply to the user with confirmation that their query has been received and logged.…

This paper provides a few approaches to automating computer programming and project submission tasks, that we have been following for the last six years and have found to be successful. The approaches include using CodeRunner with Learning…

Classification algorithms aim to predict an unknown label (e.g., a quality class) for a new instance (e.g., a product). Therefore, training samples (instances and labels) are used to deduct classification hypotheses. Often, it is relatively…

The availability of large annotated data can be a critical bottleneck in training machine learning algorithms successfully, especially when applied to diverse domains. Weak supervision offers a promising alternative by accelerating the…

Technical debt is a metaphor indicating sub-optimal solutions implemented for short-term benefits by sacrificing the long-term maintainability and evolvability of software. A special type of technical debt is explicitly admitted by software…

To advance the development of science and technology, research proposals are submitted to open-court competitive programs developed by government agencies (e.g., NSF). Proposal classification is one of the most important tasks to achieve…