Emergent morpho-phonological representations in self-supervised speech models

• URL: http://arxiv.org/abs/2509.22973v1
• Date: Fri, 26 Sep 2025 22:16:35 GMT
• Title: Emergent morpho-phonological representations in self-supervised speech models
• Authors: Jon Gauthier, Canaan Breiss, Matthew Leonard, Edward F. Chang,
• Abstract summary: We study how S3M variants optimized for word recognition represent phonological and morphological phenomena.<n>We find that their representations exhibit a global linear geometry which can be used to link English nouns and verbs to their regular inflected forms.
• Score: 3.9374885962486172
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-supervised speech models can be trained to efficiently recognize spoken words in naturalistic, noisy environments. However, we do not understand the types of linguistic representations these models use to accomplish this task. To address this question, we study how S3M variants optimized for word recognition represent phonological and morphological phenomena in frequent English noun and verb inflections. We find that their representations exhibit a global linear geometry which can be used to link English nouns and verbs to their regular inflected forms. This geometric structure does not directly track phonological or morphological units. Instead, it tracks the regular distributional relationships linking many word pairs in the English lexicon -- often, but not always, due to morphological inflection. These findings point to candidate representational strategies that may support human spoken word recognition, challenging the presumed necessity of distinct linguistic representations of phonology and morphology.

Related papers

• Probing Subphonemes in Morphology Models [3.937454839700144]
  We introduce a language-agnostic probing method to investigate phonological feature encoding in transformers trained directly on phonemes.<n>We show that phonological features which are local, such as final-obstruent devoicing in Turkish, are captured well in phoneme embeddings, whereas long-distance dependencies like vowel harmony are better represented in the transformer's encoder.
  arXiv  Detail & Related papers  (2025-05-16T14:27:40Z)
• BabyLM's First Words: Word Segmentation as a Phonological Probing Task [2.335764524038488]
  We show how word segmentation can be used as a phonological probing task.<n>We study the representations learned by phoneme-based language models trained on child-directed speech across 31 languages.
  arXiv  Detail & Related papers  (2025-04-04T10:42:56Z)
• Unsupervised Mapping of Arguments of Deverbal Nouns to Their Corresponding Verbal Labels [52.940886615390106]
  Deverbal nouns are verbs commonly used in written English texts to describe events or actions, as well as their arguments. The solutions that do exist for handling arguments of nominalized constructions are based on semantic annotation. We propose to adopt a more syntactic approach, which maps the arguments of deverbal nouns to the corresponding verbal construction.
  arXiv  Detail & Related papers  (2023-06-24T10:07:01Z)
• Morphological Inflection with Phonological Features [7.245355976804435]
  This work explores effects on performance obtained through various ways in which morphological models get access to subcharacter phonological features. We elicit phonemic data from standard graphemic data using language-specific grammars for languages with shallow grapheme-to-phoneme mapping.
  arXiv  Detail & Related papers  (2023-06-21T21:34:39Z)
• Analogy in Contact: Modeling Maltese Plural Inflection [4.83828446399992]
  We quantify the extent to which the phonology and etymology of a Maltese singular noun may predict the morphological process. The results indicate phonological pressures shape the organization of the Maltese lexicon with predictive power.
  arXiv  Detail & Related papers  (2023-05-20T20:16:57Z)
• Transparency Helps Reveal When Language Models Learn Meaning [71.96920839263457]
  Our systematic experiments with synthetic data reveal that, with languages where all expressions have context-independent denotations, both autoregressive and masked language models learn to emulate semantic relations between expressions. Turning to natural language, our experiments with a specific phenomenon -- referential opacity -- add to the growing body of evidence that current language models do not well-represent natural language semantics.
  arXiv  Detail & Related papers  (2022-10-14T02:35:19Z)
• Color Overmodification Emerges from Data-Driven Learning and Pragmatic Reasoning [53.088796874029974]
  We show that speakers' referential expressions depart from communicative ideals in ways that help illuminate the nature of pragmatic language use. By adopting neural networks as learning agents, we show that overmodification is more likely with environmental features that are infrequent or salient.
  arXiv  Detail & Related papers  (2022-05-18T18:42:43Z)
• Testing the Ability of Language Models to Interpret Figurative Language [69.59943454934799]
  Figurative and metaphorical language are commonplace in discourse. It remains an open question to what extent modern language models can interpret nonliteral phrases. We introduce Fig-QA, a Winograd-style nonliteral language understanding task.
  arXiv  Detail & Related papers  (2022-04-26T23:42:22Z)
• Decomposing lexical and compositional syntax and semantics with deep language models [82.81964713263483]
  The activations of language transformers like GPT2 have been shown to linearly map onto brain activity during speech comprehension. Here, we propose a taxonomy to factorize the high-dimensional activations of language models into four classes: lexical, compositional, syntactic, and semantic representations. The results highlight two findings. First, compositional representations recruit a more widespread cortical network than lexical ones, and encompass the bilateral temporal, parietal and prefrontal cortices.
  arXiv  Detail & Related papers  (2021-03-02T10:24:05Z)
• A phonetic model of non-native spoken word processing [40.018538874161756]
  We train a computational model of phonetic learning, which has no access to phonology, on either one or two languages. We first show that the model exhibits predictable behaviors on phone-level and word-level discrimination tasks. We then test the model on a spoken word processing task, showing that phonology may not be necessary to explain some of the word processing effects observed in non-native speakers.
  arXiv  Detail & Related papers  (2021-01-27T11:46:21Z)
• A Simple Joint Model for Improved Contextual Neural Lemmatization [60.802451210656805]
  We present a simple joint neural model for lemmatization and morphological tagging that achieves state-of-the-art results on 20 languages. Our paper describes the model in addition to training and decoding procedures.
  arXiv  Detail & Related papers  (2019-04-04T02:03:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.