Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries.
Since shortcuts vary in coverage, productivity, and semantic meaning, it is challenging for NLU experts to systematically understand and avoid them when creating benchmark datasets.
There lacks an efficient method to help users conduct gesture exploration, which is challenging due to the intrinsically temporal evolution of gestures and their complex correlation to speech content.
In this paper, we derived four design goals for a tool that helps users improve the persuasiveness of arguments in online discussions through a survey with 123 online forum users and interviews with five debating experts.
Natural language interfaces (NLIs) provide users with a convenient way to interactively analyze data through natural language queries.
However, those models do not consider the numerical properties of numbers and cannot perform robustly on numerical reasoning tasks (e. g., math word problems and measurement estimation).
Machine learning (ML) is increasingly applied to Electronic Health Records (EHRs) to solve clinical prediction tasks.
Despite being a critical communication skill, grasping humor is challenging -- a successful use of humor requires a mixture of both engaging content build-up and an appropriate vocal delivery (e. g., pause).
Much research focuses on modeling the complex intra- and inter-modal interactions between different communication channels.
Two case studies and interviews with domain experts demonstrate the effectiveness of GNNLens in facilitating the understanding of GNN models and their errors.
With machine learning models being increasingly applied to various decision-making scenarios, people have spent growing efforts to make machine learning models more transparent and explainable.
Specifically, we model the relationship between students and questions using student interactions to construct the student-interaction-question network and further present a new GNN model, called R^2GCN, which intrinsically works for the heterogeneous networks, to achieve generalizable student performance prediction in interactive online question pools.
The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness in machine learning.
In this paper, we present a visual analytics tool for enabling hypothesis-based evaluation of machine learning (ML) models.
The modulation of voice properties, such as pitch, volume, and speed, is crucial for delivering a successful public speech.
With increasing popularity in online learning, a surge of E-learning platforms have emerged to facilitate education opportunities for k-12 (from kindergarten to 12th grade) students and with this, a wealth of information on their learning logs are getting recorded.
A hierarchical network is trained using a dataset with over 30K lasso-selection records on two different point cloud data.
Human-Computer Interaction Graphics
Our visualization system features a channel coherence view and a sentence clustering view that together enable users to obtain a quick overview of emotion coherence and its temporal evolution.
To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts.
To bridge this gap and help domain experts with their training tasks in a practical environment, we propose a visual analytics system, DeepTracker, to facilitate the exploration of the rich dynamics of CNN training processes and to identify the unusual patterns that are hidden behind the huge amount of training log.
In this paper, we present a novel deep learning-based approach to evaluate the readability of graph layouts by directly using graph images.
With the growing adoption of machine learning techniques, there is a surge of research interest towards making machine learning systems more transparent and interpretable.
We propose a technique to explain the function of individual hidden state units based on their expected response to input texts.
Often, it is difficult to explore the relationships between the learned parameters and the model performance due to a large number of parameters and different random initializations.