Related papers: Mutation Sampling Technique for the Generation of …
Scheduled sampling is a technique for avoiding one of the known problems in sequence-to-sequence generation: exposure bias. It consists of feeding the model a mix of the teacher forced embeddings and the model predictions from the previous…
In this research we use a data stream approach to mining data and construct Decision Tree models that predict software build outcomes in terms of software metrics that are derived from source code used in the software construction process.…
In group sequential designs, where several data looks are conducted for early stopping, we generally assume the vector of test statistics from the sequential analyses follows (at least approximately or asymptotially) a multivariate normal…
Given a predictor of outcome derived from a high-dimensional dataset, pre-validation is a useful technique for comparing it to competing predictors on the same dataset. For microarray data, it allows one to compare a newly derived predictor…
Testing in production-like test environments is an essential part of quality assurance processes in many industries. Provisioning of such test environments, for information-intensive services, involves setting up databases that are…
Randomly generating structured objects is important in testing and optimizing functional programs, whereas generating random $'l$-terms is more specifically needed for testing and optimizing compilers. For that a tool called QuickCheck has…
Machine learning systems regularly deal with structured data in real-world applications. Unfortunately, such data has been difficult to faithfully represent in a way that most machine learning techniques would expect, i.e. as a real-valued…
Mutation testing has emerged as a powerful technique for evaluating the effectiveness of test suites for Deep Neural Networks. Among existing approaches, the statistical mutant killing criterion of DeepCrime has leveraged statistical…
We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We focus on generating long-form text, i.e., documents with multiple paragraphs, and propose a neural model enhanced with a…
Many security and network applications require having large datasets to train the machine learning models. Limited data access is a well-known problem in the security domain. Recent studies have shown the potential of Transformer models to…
We propose a general method for constructing robust permutation tests under data corruption. The proposed tests effectively control the non-asymptotic type I error under data corruption, and we prove their consistency in power under minimal…
Estimation of structure, such as in variable selection, graphical modelling or cluster analysis is notoriously difficult, especially for high-dimensional data. We introduce stability selection. It is based on subsampling in combination with…
Structured layouts are preferable in many 2D visual contents (\eg, GUIs, webpages) since the structural information allows convenient layout editing. Computational frameworks can help create structured layouts but require heavy labor input.…
LLM-based software engineering increasingly depends on executable, context-rich bug artifacts: paired correct and buggy code, methods under test (MUTs), documentation, and metadata. These artifacts support the training and evaluation of…
Many methods of estimating causal models do not provide estimates of confidence in the resulting model. In this work, a metric is proposed for validating the output of a causal model fit; the robustness of the model structure with resampled…
Our goal is to build classification models using a combination of free-text and structured data. To do this, we represent structured data by text sentences, DataWords, so that similar data items are mapped into the same sentence. This…
Diversity has been proposed as a key criterion to improve testing effectiveness and efficiency.It can be used to optimise large test repositories but also to visualise test maintenance issues and raise practitioners' awareness about waste…
In the context of black-box testing, generating test cases through model mutation is known to produce powerful test suites but usually has the drawback of being prohibitively expensive. This paper presents a new version of the tool…
Many natural language related applications involve text generation, created by humans or machines. While in many of those applications machines support humans, yet in few others, (e.g. adversarial machine learning, social bots and trolls)…
Mixture models are often used to identify meaningful subpopulations (i.e., clusters) in observed data such that the subpopulations have a real-world interpretation (e.g., as cell types). However, when used for subpopulation discovery,…