Linguistic Analogies in Word Embeddings: Where Are They?

Riccardo Contessi, Paolo Fosci, Giuseppe Psaila

2025

Abstract

Word Embedding has greatly improved Natural-Language Processing. In word-embedding models, words are represented as vectors in a multi-dimensional space; these vectors are trained through neural networks, by means of very large corpora of textual documents. Linguistic analogies are claimed to be encoded within word-embedding models, in such a way that they can be dealt with through simple vector-offset operations. This paper aims to give an answer to the following research question: given a word-embedding model, are linguistic analogies really present? It seems rather unrealistic that complex semantic relationships are encoded within a word-embedding model, which is trained to encode positional relationships between words. The investigation methodology is presented, and the results are discussed. This leads to the following question: “Linguistic analogies in Word Embeddings: where are they?”.

Paper Citation

in Harvard Style

Contessi R., Fosci P. and Psaila G. (2025). Linguistic Analogies in Word Embeddings: Where Are They?. In Proceedings of the 21st International Conference on Web Information Systems and Technologies - Volume 1: WEBIST; ISBN 978-989-758-772-6, SciTePress, pages 447-458. DOI: 10.5220/0013830300003985

in Bibtex Style

@conference{webist25,
author={Riccardo Contessi and Paolo Fosci and Giuseppe Psaila},
title={Linguistic Analogies in Word Embeddings: Where Are They?},
booktitle={Proceedings of the 21st International Conference on Web Information Systems and Technologies - Volume 1: WEBIST},
year={2025},
pages={447-458},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013830300003985},
isbn={978-989-758-772-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 21st International Conference on Web Information Systems and Technologies - Volume 1: WEBIST
TI - Linguistic Analogies in Word Embeddings: Where Are They?
SN - 978-989-758-772-6
AU - Contessi R.
AU - Fosci P.
AU - Psaila G.
PY - 2025
SP - 447
EP - 458
DO - 10.5220/0013830300003985
PB - SciTePress