Search results

In this paper we present Fantom, a social chatbot competing in the Amazon Alexa Prize 2018. The system uses a dialog graph for retrieving an approximation of the current dialog context in order to find suitable response candidates in this context. The graph is gradually built using user utterances from actual interactions, and system responses suggested by crowd workers. To this end, we developed an automatic

Gunrock is a social bot designed to engage users in open domain conversations. We improved our bot iteratively using large scale user interaction data to be more capable and human-like. Our system engaged in over 40,000 conversations during the semi-finals period of the 2018 Alexa Prize. We developed a context-aware hierarchical dialog manager to handle a wide variety of user behaviors, such as topic switching

This paper describes the Tartan conversational agent built for the 2018 Alexa Prize Competition. Tartan is a non-goal-oriented socialbot focused around providing users with an engaging and fluent casual conversation. Tartan’s key features include an emphasis on structured conversation based on flexible finite-state models and an approach focused on understanding and using conversational acts. To provide

We present BYU-EVE, an open domain dialogue architecture that combines the strengths of hand-crafted rules, deep learning, and structured knowledge graph traversal in order to create satisfying user experiences. Rather than viewing dialogue as a strict mapping between input and output texts, EVE treats conversations as a collaborative process in which two jointly coordinating agents chart a trajectory through

The Alexa Meaning Representation Language (AMRL) is a compositional graph-based semantic representation that includes fine-grained types, properties, actions, and roles and can represent a wide variety of spoken language. AMRL increases the ability of virtual assistants to represent more complex requests, including logical and conditional statements as well as ones with nested clauses. Due to this representational

Training discriminative classifiers involves learning a conditional distribution p(yi|xi), given a set of feature vectors xi and the corresponding labels yi, i = 1..N. For a classifier to be generalizable and not overfit to training data, the resulting conditional distribution p(yi|xi) is desired to be smoothly varying over the inputs xi. Adversarial training procedures enforce this smoothness using manifold

This paper presents a novel deep neural network (DNN) architecture with highway blocks (HWs) using a complex discrete Fourier transform (DFT) feature for keyword spotting. In our previous work, we showed that the feed-forward DNN with a time-delayed bottleneck layer (TDB-DNN) directly trained from the audio input outperformed the model with the log-mel filter bank energy feature (LFBE), given a large amount

We propose to smooth out the calibration score, which measures how good a forecaster is, by combining nearby forecasts. While regular calibration can be guaranteed only by randomized forecasting procedures, we show that smooth calibration can be guaranteed by deterministic procedures. As a consequence, it does not matter if the forecasts are leaked, i.e., made known in advance: smooth calibration can nevertheless

Identifying sets of items that are equivalent to one another is a problem common to many fields. Systems addressing this generally have at their core a function s(di, dj ) for computing the similarity between pairs of records di, dj . The output of s() can be interpreted as a weighted graph where edges indicate the likelihood of two records matching. Partitioning this graph into equivalence classes is non-trivial

Extraction of missing attribute values is to find values describing an attribute of interest from a free text input. Most past related work on extraction of missing attribute values work with a closed world assumption with the possible set of values known beforehand, or use dictionaries of values and hand-crafted features. How can we discover new attribute values that we have never seen before? Can we do

How do we spot interesting events from e-mail or transportation logs? How can we detect port scan or denial of service attacks from IP-IP communication data? In general, given a sequence of weighted, directed or bipartite graphs, each summarizing a snapshot of activity in a time window, how can we spot anomalous graphs containing the sudden appearance or disappearance of large dense subgraphs (e.g., near

With recent advances in network architectures for Neural Machine Translation (NMT) recurrent models have effectively been replaced by either convolutional or self-attentional approaches, such as in the Transformer. While the main innovation of the Transformer architecture is its use of self-attentional layers, there are several other aspects, such as attention with multiple heads and the use of many attention

Repeat purchasing, i.e., a customer purchasing the same product multiple times, is a common phenomenon in retail. As more customers start purchasing consumable products (e.g., toothpastes, diapers, etc.) online, this phenomenon has also become prevalent in e-commerce. However, in January 2014, when we looked at popular e-commerce websites, we did not find any customer-facing features that recommended products

Bayesian optimization (BO) is a model-based approach for gradient-free black-box function optimization, such as hyperparameter optimization. Typically, BO relies on conventional Gaussian process (GP) regression, whose algorithmic complexity is cubic in the number of evaluations. As a result, GP-based BO cannot leverage large numbers of past function evaluations, for example, to warm-start related BO runs

We consider the teacher-student framework for knowledge transfer, where the goal is to improve learning of a “student” neural network, given a “teacher” neural network pretrained on the same or a similar task. The majority of existing approaches for distilling knowledge from a teacher network to a student network rely on matching either activations or handcrafted features from the teacher network. Instead

Extreme multi-label classification (XMC) aims at assigning to an instance the most relevant subset of labels from a colossal label set. There have been some success in formulating the multi-label problem as sequence-to-sequence (Seq2Seq) learning, where the positive class labels of each input instance are used as the corresponding output sequence. Seq2Seq methods, nonetheless, have not yet been scalable

We tackle the problem of optimizing a blackbox objective function defined over a highly structured input space. This problem is ubiquitous in machine learning. Inferring the structure of a neural network or the Automatic Statistician (AS), where the kernel combination for a Gaussian process is optimized, are two of many possible examples. We use the AS as a case study to describe our approach, that can

We derive algorithms for producing optimal aggregation schedules for automatically aggregating gradients across di!erent compute units, both CPUs and GPUs, with arbitrary topologies. We show that this can be accomplished by solving a linear program on the spanning tree polytope. We give analytic bounds for the value of the optimal solution for arbitrary graphs. We also propose simple schedules that meet

Faced with distribution shift between training and test set, we wish to detect and quantify the shift, and to correct our classifiers without test set labels. Motivated by medical diagnosis, where diseases (targets), cause symptoms (observations), we focus on label shift, where the label marginal p(y) changes but the conditional p(x|y) does not. We propose Black Box Shift Estimation (BBSE) to estimate the

Training large neural networks requires distributing learning across multiple workers, where the cost of communicating gradients can be a significant bottleneck. SIGNSGD alleviates this problem by transmitting just the sign of each minibatch stochastic gradient. We prove that it can get the best of both worlds: compressed gradients and SGD-level convergence rate. The relative `1/`2 geometry of gradients