mlsanityData to 7 Oct 2026

Analyzing analytical methods: The case of phonology in neural models of spoken language

arXiv 2004.07070 ↗First posted 15 Apr 2020cs.CL cs.LG cs.SDcited by 16

Not on the map. Why?

Abstract (arXiv)

Given the fast development of analysis techniques for NLP and speech processing systems, few systematic studies have been conducted to compare the strengths and weaknesses of each method. As a step in this direction we study the case of representations of phonology in neural network models of spoken language. We use two commonly applied analytical techniques, diagnostic classifiers and representational similarity analysis, to quantify to what extent neural activation patterns encode phonemes and phoneme sequences. We manipulate two factors that can affect the outcome of analysis. First, we investigate the role of learning by comparing neural activations extracted from trained versus randomly-initialized models. Second, we examine the temporal scope of the activations by probing both local activations corresponding to a few milliseconds of the speech signal, and global activations pooled over the whole utterance. We conclude that reporting analysis results with randomly initialized models is crucial, and that global-scope methods tend to yield more consistent results and we recommend their use as a complement to local-scope diagnostic methods.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 1; 2023: 2; 2024: 3; 2025: 1; 2026: 3.

16 papers.

Sort:

By area:

  1. 2021Probing Classifiers: Promises, Shortcomings, and Advancescited by 831
  2. 2021Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniquescited by 32
  3. 2023Beyond Surface Statistics: Scene Representations in a Latent Diffusion Modelcited by 29
  4. 2024Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0cited by 19
  5. 2023Wave to Syntax: Probing spoken language models for syntaxcited by 18
  6. 2021Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representationscited by 16
  7. 2021Can phones, syllables, and words emerge as side-products of cross-situational audiovisual learning? -- A computational investigationcited by 12
  8. 2021How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddingscited by 8
  9. 2021Discrete representations in neural models of spoken languagecited by 3
  10. 2024A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speechcited by 2
  11. 2024Using Shapley interactions to understand how models use structurecited by 1
  12. 2026Prompting Underestimates LLM Capability for Time Series Classificationcited by 1
4 more
  1. 2022Modelling word learning and recognition using visually grounded speechcited by 0
  2. 2025Designing and Contextualising Probes for African Languagescited by 0
  3. 2026Tracking the emergence of linguistic structure in self-supervised models learning from speechcited by 0
  4. 2026A framework for analyzing concept representations in neural modelscited by 0