Related papers: Asterisk*: Keep it Simple
This paper proposes AS-ASR, a lightweight aphasia-specific speech recognition framework based on Whisper-tiny, tailored for low-resource deployment on edge devices. Our approach introduces a hybrid training strategy that systematically…
Intent classification is an important task in natural language understanding systems. Existing approaches have achieved perfect scores on the benchmark datasets. However they are not suitable for deployment on low-resource devices like…
Short text messages such as tweets are very noisy and sparse in their use of vocabulary. Traditional textual representations, such as tf-idf, have difficulty grasping the semantic meaning of such texts, which is important in applications…
Graph embedding is a popular algorithmic approach for creating vector representations for individual vertices in networks. Training these algorithms at scale is important for creating embeddings that can be used for classification, ranking,…
While Large Language Models and their underlying Transformer architecture are remarkably efficient, they do not reflect how our brain processes and learns a diversity of cognitive tasks such as language, nor how it leverages working memory.…
E-commerce information retrieval (IR) systems struggle to simultaneously achieve high accuracy in interpreting complex user queries and maintain efficient processing of vast product catalogs. The dual challenge lies in precisely matching…
Pixel-based language models process text rendered as images, which allows them to handle any script, making them a promising approach to open vocabulary language modelling. However, recent approaches use text renderers that produce a large…
The raster model is commonly used for the representation of images in many domains, and is especially useful in Geographic Information Systems (GIS) to store information about continuous variables of the space (elevation, temperature,…
Despite the prominence of neural network approaches in the field of recommender systems, simple methods such as matrix factorization with quadratic loss are still used in industry for several reasons. These models can be trained with…
The increasing prevalence of video clips has sparked growing interest in text-video retrieval. Recent advances focus on establishing a joint embedding space for text and video, relying on consistent embedding representations to compute…
We propose a new embedding method which is particularly well-suited for settings where the sample size greatly exceeds the ambient dimension. Our technique consists of partitioning the space into simplices and then embedding the data points…
Recently, neural network approaches for parsing have largely automated the combination of individual features, but still rely on (often a larger number of) atomic features created from human linguistic intuition, and potentially omitting…
Embeddings are functions that map raw input data to low-dimensional vector representations, while preserving important semantic information about the inputs. Pre-training embeddings on a large amount of unlabeled data and fine-tuning them…
Embedding representations power machine intelligence in many applications, including recommendation systems, but they are space intensive -- potentially occupying hundreds of gigabytes in large-scale settings. To help manage this outsized…
Short text clustering has become increasingly important with the popularity of social media like Twitter, Google+, and Facebook. Existing methods can be broadly categorized into two paradigms: topic model-based approaches and deep…
Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…
We propose an accurate and efficient scene text detection framework, termed FAST (i.e., faster arbitrarily-shaped text detector). Different from recent advanced text detectors that used complicated post-processing and hand-crafted network…
Efficient distributed numerical word representation models (word embeddings) combined with modern machine learning algorithms have recently yielded considerable improvement on automatic document classification tasks. However, the…
Communicating complex system designs or scientific processes through text alone is inefficient and prone to ambiguity. A system that automatically generates scientific architecture diagrams from text with high semantic fidelity can be…
Word embedding parameters often dominate overall model sizes in neural methods for natural language processing. We reduce deployed model sizes of text classifiers by learning a hard word clustering in an end-to-end manner. We use the…