Related papers: Attention-based Conditioning Methods for External …

Synthesising a text-to-image model of high-quality images by guiding the generative model through the Text description is an innovative and challenging task. In recent years, AttnGAN based on the Attention mechanism to guide GAN training…

Gating mechanisms are widely used in neural network models, where they allow gradients to backpropagate more easily through depth or time. However, their saturation property introduces problems of its own. For example, in recurrent models…

Recent papers in neural machine translation have proposed the strict use of attention mechanisms over previous standards such as recurrent and convolutional neural networks (RNNs and CNNs). We propose that by running traditionally stacked…

Image captioning is a challenging task at the intersection of computer vision and natural language processing, requiring models to generate meaningful textual descriptions of images. Traditional approaches rely on recurrent neural networks…

We propose an adaptation method for factorized neural transducers (FNT) with external language models. We demonstrate that both neural and n-gram external LMs add significantly more value when linearly interpolated with predictor output…

Factorization Machines (FMs) are a supervised learning approach that enhances the linear regression model by incorporating the second-order feature interactions. Despite effectiveness, FM can be hindered by its modelling of all feature…

In this study, we propose a novel multi-modal end-to-end neural approach for automated assessment of non-native English speakers' spontaneous speech using attention fusion. The pipeline employs Bi-directional Recurrent Convolutional Neural…

Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is…

In neuroscience, attention has been shown to bidirectionally interact with reinforcement learning (RL) processes. This interaction is thought to support dimensionality reduction of task representations, restricting computations to relevant…

Hand-crafted features based on linguistic and domain-knowledge play crucial role in determining the performance of disease name recognition systems. Such methods are further limited by the scope of these features or in other words, their…

This paper presents a novel approach to neural network pruning by integrating a graph-based observation space into an AutoML framework to address the limitations of existing methods. Traditional pruning approaches often depend on…

We introduce a neural reading comprehension model that integrates external commonsense knowledge, encoded as a key-value memory, in a cloze-style setting. Instead of relying only on document-to-question interaction or discrete features as…

Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks. Recent approaches that focus on modeling global context, such as self-attention and non-local operation, achieve this goal by…

While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene. Instance…

Visual attention brings significant progress for Convolution Neural Networks (CNNs) in various applications. In this paper, object-based attention in human visual cortex inspires us to introduce a mechanism for modification of activations…

One of the key challenges in natural language processing (NLP) is to yield good performance across application domains and languages. In this work, we investigate the robustness of the mention detection systems, one of the fundamental tasks…

Targeted sentiment classification predicts the sentiment polarity on given target mentions in input texts. Dominant methods employ neural networks for encoding the input sentence and extracting relations between target mentions and their…

Adverse drug events (ADEs) are an important aspect of drug safety. Various texts such as biomedical literature, drug reviews, and user posts on social media and medical forums contain a wealth of information about ADEs. Recent studies have…

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input. Prior work strives to attribute model decisions…

To assist humans in efficiently validating RAG-generated content, developing a fine-grained attribution mechanism that provides supporting evidence from retrieved documents for every answer span is essential. Existing fine-grained…