Related papers: Improving Slot Filling Performance with Attentive …

Graph Neural Networks (GNN) have recently gained popularity in the forecasting domain due to their ability to model complex spatial and temporal patterns in tasks such as traffic forecasting and region-based demand forecasting. Most of…

The energy-efficient and brain-like information processing abilities of Spiking Neural Networks (SNNs) have attracted considerable attention, establishing them as a crucial element of brain-inspired computing. One prevalent challenge…

Spiking Neural Networks (SNNs), as one of the algorithmic models in neuromorphic computing, have gained a great deal of research attention owing to temporal information processing capability, low power consumption, and high biological…

Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the…

Neural architecture search (NAS) has shown great promise in designing state-of-the-art (SOTA) models that are both accurate and efficient. Recently, two-stage NAS, e.g. BigNAS, decouples the model training and searching process and achieves…

Non-local operations are usually used to capture long-range dependencies via aggregating global context to each position recently. However, most of the methods cannot preserve object shapes since they only focus on feature similarity but…

With the increased penetration of wind energy into the power grid, it has become increasingly important to be able to predict the expected power production for larger wind farms. Deep learning (DL) models can learn complex patterns in the…

Neural-based models have achieved outstanding performance on slot filling and intent classification, when fairly large in-domain training data are available. However, as new domains are frequently added, creating sizeable data is expensive.…

Feature selection is important step in machine learning since it has shown to improve prediction accuracy while depressing the curse of dimensionality of high dimensional data. The neural networks have experienced tremendous success in…

In this paper, gating mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, a gated convolution neural network (GCNN) is employed for modeling the frame-level embedding…

Slot filling is identifying contiguous spans of words in an utterance that correspond to certain parameters (i.e., slots) of a user request/query. Slot filling is one of the most important challenges in modern task-oriented dialog systems.…

Users frequently interact with software systems through data entry forms. However, form filling is time-consuming and error-prone. Although several techniques have been proposed to auto-complete or pre-fill fields in the forms, they provide…

In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i.e., the ability to recognize and focus on key pixel regions in an image. However, in this paper, we quantitatively and…

Characters do not convey meaning, but sequences of characters do. We propose an unsupervised distributional method to learn the abstract meaningful units in a sequence of characters. Rather than segmenting the sequence, our Dynamic Capacity…

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…

Feature selection is the problem of selecting a subset of features for a machine learning model that maximizes model quality subject to a budget constraint. For neural networks, prior methods, including those based on $\ell_1$…

This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting (KWS) in limited resource environments. We employ a differentiable NAS approach to optimize the structure of…

In recent years, convolutional neural networks (CNNs) took over the field of document analysis and they became the predominant model for word spotting. Especially attribute CNNs, which learn the mapping between a word image and an attribute…

Neural Architecture Search (NAS) is a popular tool for automatically generating Neural Network (NN) architectures. In early NAS works, these tools typically optimized NN architectures for a single metric, such as accuracy. However, in the…

Recurrent neural network (RNN) based joint intent classification and slot tagging models have achieved tremendous success in recent years for building spoken language understanding and dialog systems. However, these models suffer from poor…