mlsanityData to 14 Oct 2026

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

arXiv 2304.14333 ↗First posted 27 Apr 2023cs.CL cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 18 of its 54 references that are in the map. First posted on arXiv 27 Apr 2023.

Builds on

18 of 54 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2020A Primer in BERTology: What we know about how BERT workscited by 815
  4. 2014Distributed Representations of Sentences and Documentscited by 678
  5. 2018What you can cram into a single vector: Probing sentence embeddings for linguistic propertiescited by 457
  6. 2018Analysis Methods in Neural Language Processing: A Surveycited by 277
  7. 2016Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Taskscited by 216
  8. 2020Analyzing Individual Neurons in Pre-trained Language Modelscited by 97
  9. 2020Intrinsic Probing through Dimension Selectioncited by 45
  10. 2022SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embeddingcited by 36
  11. 2018Factors Influencing the Surprising Instability of Word Embeddingscited by 33
  12. 2019Still a Pain in the Neck: Evaluating Text Representations on Lexical Compositioncited by 27
6 more
  1. 2018Language Modeling Teaches You More Syntax than Translation Does: Lessons Learned Through Auxiliary Task Analysiscited by 17
  2. 2016Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detectioncited by 13
  3. 2018Classifying Idiomatic and Literal Expressions Using Topic Models and Intensity of Emotionscited by 13
  4. 2016Nine Features in a Random Forest to Learn Taxonomical Semantic Relationscited by 7
  5. 2022Probing with Noise: Unpicking the Warp and Weft of Embeddingscited by 3
  6. 2023Probing Taxonomic and Thematic Embeddings for Taxonomic Informationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024Semantics of Multiword Expressions in Transformer-Based Models: A Surveycited by 9
  2. 2024Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Losscited by 7
  3. 2026To What Extent Do Large Language Models Understand Bangla Idioms?cited by 0