Today's deep neural networks perform incredible feats when provided sufficient training data. Sadly, annotating enough raw data to train your favorite classifier can often be prohibitively expensive, especially in important scenarios like computer-assisted medical diagnoses where labeling requires the advice of human experts. This issue has led to a surge of interest in active learning, a paradigm introduced to mitigate extravagant labeling costs. Active learning, originally studied by Angluin in 1988 [1], is in essence formed around two basic hypotheses: raw (unlabeled) data is cheap, and not all data is equally useful. The idea is that by adaptively selecting only the most informative data to label, we can get the same accuracy without the prohibitive cost.

Today's deep neural networks perform incredible feats when provided sufficient training data. Sadly, annotating enough raw data to train your favorite classifier can often be prohibitively expensive, especially in important scenarios like computer-assisted medical diagnoses where labeling requires the advice of human experts. This issue has led to a surge of interest in active learning, a paradigm introduced to mitigate extravagant labeling costs. Active learning, originally studied by Angluin in 1988 [1], is in essence formed around two basic hypotheses: raw (unlabeled) data is cheap, and not all data is equally useful. The idea is that by adaptively selecting only the most informative data to label, we can get the same accuracy without the prohibitive cost.

Human communication relies on common ground (CG), the mutual knowledge and beliefs shared by participants, to produce coherent and interesting conversations. In this paper, we demonstrate that current response generation (RG) models produce generic and dull responses in dialogues because they act reflexively, failing to explicitly model CG, both due to the lack of CG in training data and the standard RG training procedure. We introduce Reflect, a dataset that annotates dialogues with explicit CG (materialized as inferences approximating shared knowledge and beliefs) and solicits 9k diverse human-generated responses each following one common ground. Using Reflect, we showcase the limitations of current dialogue data and RG models: less than half of the responses in current data are rated as high quality (sensible, specific, and interesting) and models trained using this data have even lower quality, while most Reflect responses are judged high quality. Next, we analyze whether CG can help models produce better-quality responses by using Reflect CG to guide RG models. Surprisingly, we find that simply prompting GPT3 to "think" about CG generates 30% more quality responses, showing promising benefits to integrating CG into the RG process.

We initiate the study of active learning polynomial threshold functions (PTFs). While traditional lower bounds imply that even univariate quadratics cannot be non-trivially actively learned, we show that allowing the learner basic access to the derivatives of the underlying classifier circumvents this issue and leads to a computationally efficient algorithm for active learning degree-$d$ univariate PTFs in $\tilde{O}(d^3\log(1/\varepsilon\delta))$ queries. We also provide near-optimal algorithms and analyses for active learning PTFs in several average case settings. Finally, we prove that access to derivatives is insufficient for active learning multivariate PTFs, even those of just two variables.

With the explosion of massive, widely available unlabeled data in the past years, finding label and time efficient, robust learning algorithms has become ever more important in theory and in practice. We study the paradigm of active learning, in which algorithms with access to large pools of data may adaptively choose what samples to label in the hope of exponentially increasing efficiency. By introducing comparisons, an additional type of query comparing two points, we provide the first time and query efficient algorithms for learning non-homogeneous linear separators robust to bounded (Massart) noise. We further provide algorithms for a generalization of the popular Tsybakov low noise condition, and show how comparisons provide a strong reliability guarantee that is often impractical or impossible with only labels - returning a classifier that makes no errors with high probability.

To facilitate this, Rashkin et al. (2018) build the Event2Mind dataset and Sap et al. (2018) present the Atomic dataset, mainly focus on nine If-Then reasoning types to describe causes, effects, intents and participant characteristic about events. Together with these datasets, a simple RNN-based encoder-decoder framework is proposed to conduct the If-Then reasoning. However, there still remains two challenging problems. First, as illustrated in Figure 1, given an event "PersonX finds a new job", the plausible feeling of PersonX about that event could be multiple (such as "needy/stressed out" and "relieved/joyful"). Previous work showed that for the one-to-many problem, conventional RNN-based encoder-decoder models tend to generate generic responses, rather than meaningful and specific answers (Li et al., 2016; Serban et al., 2016). Second, as a commonsense reasoning problem, rich background knowledge is necessary for generating reasonable inferences. For example, as shown in Figure 1, the feeling of PersonX upon the event "PersonX finds a new job" could be multiple. However, after given a context " PersonX was fired", the plausible inferences would be narrowed down to " needy" or " stressed out ". To better solve these problems, we propose a context-aware variational autoencoder (CWV AE) together with a two-stage training procedure.

In recent years, the availability of big data and the high cost of labeling has lead to a surge of interest in active learning, an adaptive, semi-supervised learning paradigm. In traditional active learning, given an instance space X, a distribution D on X, and a class of concepts c: X {0, 1}, the learner receives unlabeled samples x from D with the ability to query an oracle for the labeling c(x). Classically our goal would be to minimize the number of samples the learner draws before approximately learning the concept class with high probability (PAClearning). Instead, active learning assumes unlabeled samples are inexpensive, and rather aims to minimize expensive queries to the oracle. While active learning requires exponentially fewer labeled samples than PAClearning for simple classes such as intervals and thresholds, it fails to provide asymptotic improvement for classes essential to machine learning such as linear separators [1]. However, recent results point to the fact that with slight relaxations or additions to the paradigm, such concept classes can be learned with exponentially fewer queries.