On Self-improving Token Embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kubek, Mario M., Pokharel, Shiraj, Böhme, Thomas, McDaniel, Emma L., Unger, Herwig, Mikler, Armin R.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910915353378816
author Kubek, Mario M.
Pokharel, Shiraj
Böhme, Thomas
McDaniel, Emma L.
Unger, Herwig
Mikler, Armin R.
author_facet Kubek, Mario M.
Pokharel, Shiraj
Böhme, Thomas
McDaniel, Emma L.
Unger, Herwig
Mikler, Armin R.
contents This article introduces a novel and fast method for refining pre-trained static word or, more generally, token embeddings. By incorporating the embeddings of neighboring tokens in text corpora, it continuously updates the representation of each token, including those without pre-assigned embeddings. This approach effectively addresses the out-of-vocabulary problem, too. Operating independently of large language models and shallow neural networks, it enables versatile applications such as corpus exploration, conceptual search, and word sense disambiguation. The method is designed to enhance token representations within topically homogeneous corpora, where the vocabulary is restricted to a specific domain, resulting in more meaningful embeddings compared to general-purpose pre-trained vectors. As an example, the methodology is applied to explore storm events and their impacts on infrastructure and communities using narratives from a subset of the NOAA Storm Events database. The article also demonstrates how the approach improves the representation of storm-related terms over time, providing valuable insights into the evolving nature of disaster narratives.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14808
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On Self-improving Token Embeddings
Kubek, Mario M.
Pokharel, Shiraj
Böhme, Thomas
McDaniel, Emma L.
Unger, Herwig
Mikler, Armin R.
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
68T50, 68T07
I.2.6; I.2.7; H.3.3
This article introduces a novel and fast method for refining pre-trained static word or, more generally, token embeddings. By incorporating the embeddings of neighboring tokens in text corpora, it continuously updates the representation of each token, including those without pre-assigned embeddings. This approach effectively addresses the out-of-vocabulary problem, too. Operating independently of large language models and shallow neural networks, it enables versatile applications such as corpus exploration, conceptual search, and word sense disambiguation. The method is designed to enhance token representations within topically homogeneous corpora, where the vocabulary is restricted to a specific domain, resulting in more meaningful embeddings compared to general-purpose pre-trained vectors. As an example, the methodology is applied to explore storm events and their impacts on infrastructure and communities using narratives from a subset of the NOAA Storm Events database. The article also demonstrates how the approach improves the representation of storm-related terms over time, providing valuable insights into the evolving nature of disaster narratives.
title On Self-improving Token Embeddings
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
68T50, 68T07
I.2.6; I.2.7; H.3.3
url https://arxiv.org/abs/2504.14808