Related papers: Robust Educational Dialogue Act Classifiers with L…

Short text clustering is challenging since it takes imbalanced and noisy data as inputs. Existing approaches cannot solve this problem well, since (1) they are prone to obtain degenerate solutions especially on heavy imbalanced datasets,…

Reward-driven proactive dialogue agents require precise estimation of user satisfaction as an intrinsic reward signal to determine optimal interaction strategies. Specifically, this framework triggers clarification questions when detecting…

Causal Abstraction (CA) theory provides a principled framework for relating causal models that describe the same system at different levels of granularity while ensuring interventional consistency between them. Recent methods for learning…

Current state-of-the-art neural dialogue models learn from human conversations following the data-driven paradigm. As such, a reliable training corpus is the crux of building a robust and well-behaved dialogue model. However, due to the…

Classification tasks are common across many fields and applications where the decision maker's action is limited by resource constraints. In direct marketing only a subset of customers is contacted; scarce human resources limit the number…

Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer. CRF models the conditional probability of the…

This paper deals with multi-lingual dialogue act (DA) recognition. The proposed approaches are based on deep neural networks and use word2vec embeddings for word representation. Two multi-lingual models are proposed for this task. The first…

We consider the problem of Probably Approximate Correct (PAC) learning of a binary classifier from noisy labeled examples acquired from multiple annotators (each characterized by a respective classification noise rate). First, we consider…

Recent machine learning algorithms have been developed using well-curated datasets, which often require substantial cost and resources. On the other hand, the direct use of raw data often leads to overfitting towards frequently occurring…

Dataset bias is one of the prevailing causes of unfairness in machine learning. Addressing fairness at the data collection and dataset preparation stages therefore becomes an essential part of training fairer algorithms. In particular,…

Training and evaluation of fair classifiers is a challenging problem. This is partly due to the fact that most fairness metrics of interest depend on both the sensitive attribute information and label information of the data points. In many…

In document classification for, e.g., legal and biomedical text, we often deal with hundreds of classes, including very infrequent ones, as well as temporal concept drift caused by the influence of real world events, e.g., policy changes,…

Cost-sensitive learning relies on the availability of a known and fixed cost matrix. However, in some scenarios, the cost matrix is uncertain during training, and re-train a classifier after the cost matrix is specified would not be an…

Fairness-aware mining of massive data streams is a growing and challenging concern in the contemporary domain of machine learning. Many stream learning algorithms are used to replace humans at critical decision-making points e.g., hiring…

Outlier detection (OD) is one of the core challenges in machine learning. Transductive learning, which leverages test data during training, has shown promise in related machine learning tasks, yet remains largely unexplored for modern OD.…

Active domain adaptation (DA) aims to maximally boost the model adaptation on a new target domain by actively selecting limited target data to annotate, whereas traditional active learning methods may be less effective since they do not…

In this paper, we propose systematic and efficient gradient-based methods for both one-way and two-way partial AUC (pAUC) maximization that are applicable to deep learning. We propose new formulations of pAUC surrogate objectives by using…

In dialogues, an utterance is a chain of consecutive sentences produced by one speaker which ranges from a short sentence to a thousand-word post. When studying dialogues at the utterance level, it is not uncommon that an utterance would…

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement…