Related papers: Exponential Family Attention
Random-feature-based attention (RFA) is an efficient approximation of softmax attention with linear runtime and space complexity. However, the approximation gap between RFA and conventional softmax attention is not well studied. Built upon…
Deep learning techniques have considerably improved speech processing in recent years. Speaker representations extracted by deep learning models are being used in a wide range of tasks such as speaker recognition and speech emotion…
Knowing which words have been attended to in previous time steps while generating a translation is a rich source of information for predicting what words will be attended to in the future. We improve upon the attention model of Bahdanau et…
Principal Component Analysis (PCA) and its exponential family extensions have three components: observations, latents and parameters of a linear transformation. We consider a generalised setting where the canonical parameters of the…
We introduce exclusive self attention (XSA), a simple modification of self attention (SA) that improves Transformer's sequence modeling performance. The key idea is to constrain attention to capture only information orthogonal to the…
We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…
Attention mechanism has been proven effective on natural language processing. This paper proposes an attention boosted natural language inference model named aESIM by adding word attention and adaptive direction-oriented attention…
We develop a class of exponential-family point processes based on a latent social space to model the coevolution of social structure and behavior over time. Temporal dynamics are modeled as a discrete Markov process specified through…
As artificial intelligence (AI) systems become increasingly embedded in our daily life, the ability to recognize and adapt to human emotions is essential for effective human-computer interaction. Facial expression recognition (FER) provides…
Recently, representation learning over graph networks has gained popularity, with various models showing promising results. Despite this, several challenges persist: 1) most methods are designed for static or discrete-time dynamic graphs;…
In recommender systems, models mostly use a combination of embedding layers and multilayer feedforward neural networks. The high-dimensional sparse original features are downscaled in the embedding layer and then fed into the fully…
Feature attribution methods (FAs), such as gradients and attention, are widely employed approaches to derive the importance of all input features to the model predictions. Existing work in natural language processing has mostly focused on…
Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated…
In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…
The prevalence of employing attention mechanisms has brought along concerns on the interpretability of attention distributions. Although it provides insights about how a model is operating, utilizing attention as the explanation of model…
Event extraction (EE), which acquires structural event knowledge from texts, can be divided into two sub-tasks: event type classification and element extraction (namely identifying triggers and arguments under different role patterns). As…
In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…
Recurrent neural network grammars (RNNG) are a recently proposed probabilistic generative modeling family for natural language. They show state-of-the-art language modeling and parsing performance. We investigate what information they…
Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time…
Windowed attention mechanisms were introduced to mitigate the issue of excessive computation inherent in global attention mechanisms. In this paper, we present FwNet-ECA, a novel method that utilizes Fourier transforms paired with learnable…