Estimating Text Similarity based on Semantic Concept Embeddings

Tim vor der Brück, Marc Pouly
1/9/2024
cs.CLcs.AI

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

Due to their ease of use and high accuracy, Word2Vec (W2V) word embeddings enjoy great success in the semantic representation of words, sentences, and whole documents as well as for semantic similarity estimation. However, they have the shortcoming that they are directly extracted from a surface representation, which does not adequately represent human thought processes and also performs poorly for highly ambiguous words. Therefore, we propose Semantic Concept Embeddings (CE) based on the MultiNet Semantic Network (SN) formalism, which addresses both shortcomings. The evaluation on a marketing target group distribution task showed that the accuracy of predicted target groups can be increased by combining traditional word embeddings with semantic CEs.

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. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

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

Similar Papers

Evaluating the impact of word embeddings on similarity scoring in practical information retrieval

80% match2026

Partial Colexifications Improve Concept Embeddings

79% match2025

Semantic similarity prediction is better than other semantic similarity measures

79% match1 repo72023

PropNet: a White-Box and Human-Like Network for Sentence Representation

78% match2025

Interpretable Text Embeddings and Text Similarity Explanation: A Survey

78% match2025

One Word Is Not Enough: Simple Prompts Improve Word Embeddings

78% match2025

Cite this paper

@article{brck2024estimating,
  title  = {Estimating Text Similarity based on Semantic Concept Embeddings},
  author = {Tim vor der Brück and Marc Pouly},
  year   = {2024},
  eprint = {2401.04422},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2401.04422v1}
}

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/2401.04422.svg)](https://codeofpaper.com/paper/2401.04422)

Discussion