Related papers: The Wall and The Ball: A Study of Domain Referent …
Domain generalization is the problem of assigning labels to an unlabeled data set, given several similar data sets for which labels have been provided. Despite considerable interest in this problem over the last decade, there has been no…
The problem of error density estimation for a functional single index model with dependent errors is studied. A Bayesian method is utilized to simultaneously estimate the bandwidths in the kernel-form error density and regression function,…
The application of deep machine learning methods in astronomy has exploded in the last decade, with new models showing remarkably improved performance on benchmark tasks. Not nearly enough attention is given to understanding the models'…
Data Scientists often use notebooks to develop Data Science (DS) pipelines, particularly since they allow to selectively execute parts of the pipeline. However, notebooks for DS have many well-known flaws. We focus on the following ones in…
Both generic and domain-specific BERT models are widely used for natural language processing (NLP) tasks. In this paper we investigate the vulnerability of BERT models to variation in input data for Named Entity Recognition (NER) through…
Ideally Open-Domain Question Answering models should exhibit a number of competencies, ranging from simply memorizing questions seen at training time, to answering novel question formulations with answers seen during training, to…
Few major commercial or economic decisions are made today which are not underpinned by analysis using spreadsheets. It is virtually impossible to avoid making mistakes during their drafting and some of these errors remain, unseen and…
To aid the development of spreadsheet debugging tools, a knowledge of end-users natural behaviour within the Excel environment would be advantageous. This paper details the design and application of a novel data acquisition tool, which can…
Due to the large amount of daily scientific publications, it is impossible to manually review each one. Therefore, an automatic extraction of key information is desirable. In this paper, we examine STEREO, a tool for extracting statistics…
Off-the-shelf models are widely used by computational social science researchers to measure properties of text, such as sentiment. However, without access to source data it is difficult to account for domain shift, which represents a threat…
State of the art computer vision models have been shown to be vulnerable to small adversarial perturbations of the input. In other words, most images in the data distribution are both correctly classified by the model and are very close to…
Understanding your audience is foundational to creating high impact visualization designs. However, individual differences and cognitive abilities also influence interactions with information visualization. Differing user needs and…
Spoken question answering (SQA) is challenging due to complex reasoning on top of the spoken documents. The recent studies have also shown the catastrophic impact of automatic speech recognition (ASR) errors on SQA. Therefore, this work…
Dataset replication is a useful tool for assessing whether improvements in test accuracy on a specific benchmark correspond to improvements in models' ability to generalize reliably. In this work, we present unintuitive yet significant ways…
Named Entity Recognition (NER) plays an important role in a wide range of natural language processing tasks, such as relation extraction, question answering, etc. However, previous studies on NER are limited to particular genres, using…
Our work stems from the consideration that the spreading of a disease is modulated by the individual's perception of the infected neighborhood and his/her strategy to avoid being infected as well. We introduced a general ``cellular agent''…
Data sharing is fundamental to scientific progress, enhancing transparency, reproducibility, and innovation across disciplines. Despite its growing significance, the variability of data-sharing practices across research fields remains…
Many applications utilize sensors in mobile devices and machine learning to provide novel services. However, various factors such as different users, devices, and environments impact the performance of such applications, thus making the…
In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model. Through empirical analysis, we find that fine-tuning BERT tends to over-fit the error model…
Spreadsheets are widely recognized as the most popular end-user programming tools, which blend the power of formula-based computation, with an intuitive table-based interface. Today, spreadsheets are used by billions of users to manipulate…