mlsanityData to 14 Oct 2026

Tracking linguistic information in transformer-based sentence embeddings through targeted sparsification

arXiv 2407.18119 ↗First posted 25 Jul 2024cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Analyses of transformer-based models have shown that they encode a variety of linguistic information from their textual input. While these analyses have shed a light on the relation between linguistic information on one side, and internal architecture and parameters on the other, a question remains unanswered: how is this linguistic information reflected in sentence embeddings? Using datasets consisting of sentences with known structure, we test to what degree information about chunks (in particular noun, verb or prepositional phrases), such as grammatical number, or semantic role, can be localized in sentence embeddings. Our results show that such information is not distributed over the entire sentence embedding, but rather it is encoded in specific regions. Understanding how the information from an input text is compressed into sentence embeddings helps understand current transformer models and help build future explainable neural models.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 25 Jul 2024.

Builds on

27 of 40 references.

References · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  6. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  7. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,059
  8. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 1,003
  9. 2020A Primer in BERTology: What we know about how BERT workscited by 815
  10. 2023Towards Automated Circuit Discovery for Mechanistic Interpretabilitycited by 724
  11. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 583
  12. 2018What you can cram into a single vector: Probing sentence embeddings for linguistic propertiescited by 457
15 more
  1. 2019What do you learn from context? Probing for sentence structure in contextualized word representationscited by 438
  2. 2016Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Taskscited by 216
  3. 2019Assessing BERT's Syntactic Abilitiescited by 192
  4. 2023Task-Specific Skill Localization in Fine-tuned Language Modelscited by 105
  5. 2019Winning the Lottery with Continuous Sparsificationcited by 100
  6. 2020Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Maskscited by 98
  7. 2021Low-Complexity Probing via Finding Subnetworkscited by 64
  8. 2021Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERTcited by 41
  9. 2022SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Featurescited by 33
  10. 2020Toward Better Storylines with Sentence-Level Language Modelscited by 14
  11. 2023How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structurecited by 13
  12. 2023Blackbird language matrices (BLM), a new task for rule-like generalization in neural networks: Motivations and Formal Specificationscited by 9
  13. 2024Are there identifiable structural parts in the sentence embedding whole?cited by 6
  14. 2022Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structurescited by 4
  15. 2023Grammatical information in BERT sentence embeddings as two-dimensional arrayscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025Interpretable Text Embeddings and Text Similarity Explanation: A Surveycited by 12
  2. 2025Sentence Smith: Controllable Edits for Evaluating Text Embeddingscited by 4
  3. 2026Datasets for Verb Alternations across Languages: BLM Templates and Data Augmentation Strategiescited by 1
  4. 2025Mechanistic Decomposition of Sentence Representationscited by 0
  5. 2025Towards Fundamental Language Models: Does Linguistic Competence Scale with Model Size?cited by 0
  6. 2026Blackbird Language Matrices: A Framework to Investigate the Linguistic Competence of Language Modelscited by 0