Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Space

Filip Klubička, Vasudevan Nedumpozhimana, John D. Kelleher
4/27/2023
cs.CLcs.AIcs.LG

No confident code implementation found for this paper.

Abstract

The goal of this paper is to learn more about how idiomatic information is structurally encoded in embeddings, using a structural probing method. We repurpose an existing English verbal multi-word expression (MWE) dataset to suit the probing framework and perform a comparative probing study of static (GloVe) and contextual (BERT) embeddings. Our experiments indicate that both encode some idiomatic information to varying degrees, but yield conflicting evidence as to whether idiomaticity is encoded in the vector norm, leaving this an open question. We also identify some limitations of the used dataset and highlight important directions for future work in improving its suitability for a probing analysis.

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

Investigating Idiomaticity in Word Representations

83% match1 repo22024

Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context

80% match1 repo62024

A Survey of Idiom Datasets for Psycholinguistic and Computational Research

79% match2025

Semantic Structure and Interpretability of Word Embeddings

79% match1 repo102017

To What Extent Do Large Language Models Understand Bangla Idioms?

79% match2026

Is Less More? Quality, Quantity and Context in Idiom Processing with Natural Language Models

79% match1 repo12024

Cite this paper

@article{klubika2023idioms,
  title  = {Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Space},
  author = {Filip Klubička and Vasudevan Nedumpozhimana and John D. Kelleher},
  year   = {2023},
  eprint = {2304.14333},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2304.14333v1}
}

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/2304.14333.svg)](https://codeofpaper.com/paper/2304.14333)

Discussion