More Discriminative Sentence Embeddings via Semantic Graph Smoothing

Chakib Fettal, Lazhar Labiod, Mohamed Nadif
2/20/2024
cs.CLcs.LG

No confident code implementation found for this paper.

Abstract

This paper explores an empirical approach to learn more discriminantive sentence representations in an unsupervised fashion. Leveraging semantic graph smoothing, we enhance sentence embeddings obtained from pretrained models to improve results for the text clustering and classification tasks. Our method, validated on eight benchmarks, demonstrates consistent improvements, showcasing the potential of semantic graph smoothing in improving sentence embeddings for the supervised and unsupervised document categorization tasks.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Rethinking Graph-Based Document Classification: Learning Data-Driven Structures Beyond Heuristic Approaches

82% match2025

Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning

81% match2024

Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models

79% match1 repo832025

GuideWalk: A Novel Graph-Based Word Embedding for Enhanced Text Classification

78% match2024

BP-Seg: A graphical model approach to unsupervised and non-contiguous text segmentation using belief propagation

78% match2025

Graph-Convolutional Networks: Named Entity Recognition and Large Language Model Embedding in Document Clustering

78% match2024

Cite this paper

@article{fettal2024more,
  title  = {More Discriminative Sentence Embeddings via Semantic Graph Smoothing},
  author = {Chakib Fettal and Lazhar Labiod and Mohamed Nadif},
  year   = {2024},
  eprint = {2402.12890},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.12890v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.12890.svg)](https://codeofpaper.com/paper/2402.12890)

Discussion