On Self-improving Token Embeddings

• URL: http://arxiv.org/abs/2504.14808v1
• Date: Mon, 21 Apr 2025 02:17:19 GMT
• Title: On Self-improving Token Embeddings
• Authors: Mario M. Kubek, Shiraj Pokharel, Thomas Böhme, Emma L. McDaniel, Herwig Unger, Armin R. Mikler,
• Abstract summary: Article introduces a novel and fast method for refining pre-trained static word or, more generally, token embeddings.<n>It continuously updates the representation of each token, including those without pre-assigned embeddings.<n> operating independently of large language models and shallow neural networks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Mechanistic Decomposition of Sentence Representations [3.9146761527401432]
  Sentence embeddings are central to modern NLP and AI systems, but little is known about their internal structure.<n>We propose a new method to mechanistically decompose sentence embeddings into interpretable components.<n>We analyze how pooling compresses these features into sentence representations, and assess the latent features that reside in a sentence embedding.
  arXiv  Detail & Related papers  (2025-06-04T18:42:57Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space.<n>Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• CAST: Corpus-Aware Self-similarity Enhanced Topic modelling [16.562349140796115]
  We introduce CAST: Corpus-Aware Self-similarity Enhanced Topic modelling, a novel topic modelling method.<n>We find self-similarity to be an effective metric to prevent functional words from acting as candidate topic words.<n>Our approach significantly enhances the coherence and diversity of generated topics, as well as the topic model's ability to handle noisy data.
  arXiv  Detail & Related papers  (2024-10-19T15:27:11Z)
• Manual Verbalizer Enrichment for Few-Shot Text Classification [1.860409237919611]
  acrshortmave is an approach for verbalizer construction by enrichment of class labels. Our model achieves state-of-the-art results while using significantly fewer resources.
  arXiv  Detail & Related papers  (2024-10-08T16:16:47Z)
• Neural Sequence-to-Sequence Modeling with Attention by Leveraging Deep Learning Architectures for Enhanced Contextual Understanding in Abstractive Text Summarization [0.0]
  This paper presents a novel framework for abstractive TS of single documents. It integrates three dominant aspects: structure, semantic, and neural-based approaches. Results indicate significant improvements in handling rare and OOV words.
  arXiv  Detail & Related papers  (2024-04-08T18:33:59Z)
• Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation [59.37587762543934]
  This paper studies the problem of weakly open-vocabulary semantic segmentation (WOVSS) Existing methods suffer from a granularity inconsistency regarding the usage of group tokens. We propose the prototypical guidance network (PGSeg) that incorporates multi-modal regularization.
  arXiv  Detail & Related papers  (2023-10-29T13:18:00Z)
• Topic-DPR: Topic-based Prompts for Dense Passage Retrieval [6.265789210037749]
  We present Topic-DPR, a dense passage retrieval model that uses topic-based prompts. We introduce a novel positive and negative sampling strategy, leveraging semi-structured data to boost dense retrieval efficiency.
  arXiv  Detail & Related papers  (2023-10-10T13:45:24Z)
• Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning [63.148199057487226]
  We propose a modular, NEuroSymbolic Textual Agent (NESTA) that combines a generic semantic generalization with a rule induction system to learn interpretable rules as policies. Our experiments show that the proposed NESTA method outperforms deep reinforcement learning-based techniques by achieving better to unseen test games and learning from fewer training interactions.
  arXiv  Detail & Related papers  (2023-07-05T23:21:05Z)
• Transferring Semantic Knowledge Into Language Encoders [6.85316573653194]
  We introduce semantic form mid-tuning, an approach for transferring semantic knowledge from semantic meaning representations into language encoders. We show that this alignment can be learned implicitly via classification or directly via triplet loss. Our method yields language encoders that demonstrate improved predictive performance across inference, reading comprehension, textual similarity, and other semantic tasks.
  arXiv  Detail & Related papers  (2021-10-14T14:11:12Z)
• Infusing Finetuning with Semantic Dependencies [62.37697048781823]
  We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
  arXiv  Detail & Related papers  (2020-12-10T01:27:24Z)
• A Comparative Study on Structural and Semantic Properties of Sentence Embeddings [77.34726150561087]
  We propose a set of experiments using a widely-used large-scale data set for relation extraction. We show that different embedding spaces have different degrees of strength for the structural and semantic properties. These results provide useful information for developing embedding-based relation extraction methods.
  arXiv  Detail & Related papers  (2020-09-23T15:45:32Z)
• Text Classification with Few Examples using Controlled Generalization [58.971750512415134]
  Current practice relies on pre-trained word embeddings to map words unseen in training to similar seen ones. Our alternative begins with sparse pre-trained representations derived from unlabeled parsed corpora. We show that a feed-forward network over these vectors is especially effective in low-data scenarios.
  arXiv  Detail & Related papers  (2020-05-18T06:04:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.