Related papers: Symphonym: Universal Phonetic Embeddings for Cross…

Handwritten word retrieval is vital for digital archives but remains challenging due to large handwriting variability and cross-lingual semantic gaps. While large vision-language models offer potential solutions, their prohibitive…

To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned? We explore these questions by training neural models for a range of natural language processing tasks on…

Xenium, a new spatial transcriptomics platform, enables subcellular-resolution profiling of complex tumor tissues. Despite the rich morphological information in histology images, extracting robust cell-level features and integrating them…

This paper proposes Allophant, a multilingual phoneme recognizer. It requires only a phoneme inventory for cross-lingual transfer to a target language, allowing for low-resource recognition. The architecture combines a compositional phone…

This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i.e., when the response variables have dimension higher than one. In particular, we consider the…

Despite significant recent advances in the field of face recognition, implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this paper we present a system, called FaceNet,…

We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts. Our system uses a single BiLSTM encoder with a shared BPE…

With the aim to improve the performance of feature matching, we present an unsupervised approach to fuse various local descriptors in the space of homographies. Inspired by the observation that the homographies of correct feature…

The memory of contemporary Large Language Models is bound by a physical paradox: as they learn, they fill up. The linear accumulation (O(N)) of Key-Value states treats context as a warehouse of static artifacts, eventually forcing a…

Definitive embeddings remain a fundamental challenge of computational musicology for symbolic music in deep learning today. Analogous to natural language, music can be modeled as a sequence of tokens. This motivates the majority of existing…

Learning representations of geographical space is vital for any machine learning model that integrates geolocated data, spanning application domains such as remote sensing, ecology, or epidemiology. Recent work embeds coordinates using sine…

Humans can robustly recognize and localize objects by integrating visual and auditory cues. While machines are able to do the same now with images, less work has been done with sounds. This work develops an approach for dense semantic…

Centralized search engines are key for the Internet, but lead to undesirable concentration of power. Decentralized alternatives fail to offer equal document retrieval accuracy and speed. Nevertheless, Semantic Overlay Networks can come…

In research areas with scarce data, representation learning plays a significant role. This work aims to enhance representation learning for clinical time series by deriving universal embeddings for clinical features, such as heart rate and…

By implicitly recognizing a user based on his/her speech input, speaker identification enables many downstream applications, such as personalized system behavior and expedited shopping checkouts. Based on whether the speech content is…

Integrating Pre-trained Language Models (PLMs) with Graph Neural Networks (GNNs) remains a central challenge in text-rich heterophilic graph learning. We propose a novel integration framework that enables effective fusion between powerful…

Modelling taxonomic and thematic relatedness is important for building AI with comprehensive natural language understanding. The goal of this paper is to learn more about how taxonomic information is structurally encoded in embeddings. To…

Contextualized embeddings based on large language models (LLMs) are available for various languages, but their coverage is often limited for lower resourced languages. Using LLMs for such languages is often difficult due to a high…

Object naming - the act of identifying an object with a word or a phrase - is a fundamental skill in interpersonal communication, relevant to many disciplines, such as psycholinguistics, cognitive linguistics, or language and vision…

Pre-trained models (PTMs) have shown great promise in the speech and audio domain. Embeddings leveraged from these models serve as inputs for learning algorithms with applications in various downstream tasks. One such crucial task is Speech…