One of the exciting capabilities of recent language models for dialog is their ability to independently search for relevant information to ground a given dialog response. However, obtaining training data to teach models how to issue search queries is time and resource consuming. In this work, we propose q2d: an automatic data generation pipeline that generates information-seeking dialogs from questions. We prompt a large language model (PaLM) to create conversational versions of question answering datasets, and use it to improve query generation models that communicate with external search APIs to ground dialog responses. Unlike previous approaches which relied on human written dialogs with search queries, our method allows to automatically generate query-based grounded dialogs with better control and scale. Our experiments demonstrate that: (1) For query generation on the QReCC dataset, models trained on our synthetically-generated data achieve 90%--97% of the performance of models trained on the human-generated data; (2) We can successfully generate data for training dialog models in new domains without any existing dialog data as demonstrated on the multi-hop MuSiQue and Bamboogle QA datasets. (3) We perform a thorough analysis of the generated dialogs showing that humans find them of high quality and struggle to distinguish them from human-written dialogs.

We examine the surveying problem, where we attempt to predict how a target user is likely to respond to questions by iteratively querying that user, collaboratively based on the responses of a sample set of users. We focus on an active learning approach, where the next question we select to ask the user depends on their responses to the previous questions. We propose a method for solving the problem based on a Bayesian dimensionality reduction technique. We empirically evaluate our method, contrasting it to benchmark approaches based on augmented linear regression, and show that it achieves much better predictive performance, and is much more robust when there is missing data.

We propose a system for determining properties of mathematical functions given an image of their graph representation. We demonstrate our approach for two-dimensional graphs (curves of single variable functions) and three-dimensional graphs (surfaces of two variable functions), studying the properties of convexity and symmetry. Our method uses a Convolutional Neural Network which classifies functions according to these properties, without using any hand-crafted features. We propose algorithms for randomly constructing functions with convexity or symmetry properties, and use the images generated by these algorithms to train our network. Our system achieves a high accuracy on this task, even for functions where humans find it difficult to determine the function's properties from its image.

We demonstrate a system for predicting gaming related properties from Twitter accounts. Our system predicts various traits of users based on the tweets publicly available in their profiles. Such inferred traits include degrees of tech-savviness and knowledge on computer games, actual gaming performance, preferred platform, degree of originality, humor and influence on others. Our system is based on machine learning models trained on crowd-sourced data. It allows people to select Twitter accounts of their fellow gamers, examine the trait predictions made by our system, and the main drivers of these predictions. We present empirical results on the performance of our system based on its accuracy on our crowd-sourced dataset.

We consider the task of predicting various traits of a person given an image of their face. We aim to estimate traits such as gender, ethnicity and age, as well as more subjective traits as the emotion a person expresses or whether they are humorous or attractive. Due to the recent surge of research on Deep Convolutional Neural Networks (CNNs), we begin by using a CNN architecture, and corroborate that CNNs are promising for facial attribute prediction. To further improve performance, we propose a novel approach that incorporates facial landmark information for input images as an additional channel, helping the CNN learn face-specific features so that the landmarks across various training images hold correspondence. We empirically analyze the performance of our proposed method, showing consistent improvement over the baselines across traits. We demonstrate our system on a sizeable Face Attributes Dataset (FAD), comprising of roughly 200,000 labels, for 10 most sought-after traits, for over 10,000 facial images.