Challenge: a recent study shows that self-supervised speech models do not represent phonological and morphological phenomena in frequent English noun and verb inflections.
Approach: They study how S3Ms represent phonological and morphological phenomena in English . they propose alternative representational strategies that may support human spoken word recognition .
Outcome: a new study shows that S3M models can represent phonological and morphological phenomena in English . the models can be trained to recognize spoken words in naturalistic, noisy environments .

Similar Papers

[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies on how self-supervised speech models encode rich phonetic information have not explored how they are structured.
Approach: They conduct a comprehensive analysis of the underlying structure of S3M representations with particular attention to phonological vectors.
Outcome: The proposed model encodes phonologically interpretable and compositional vectors, demonstrating phonology vector arithmetic.
Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations (2025.emnlp-main)

Copied to clipboard

Challenge: a recent study evaluated the extent to which SLMs encode nuanced syntactic and conceptual features . acoustic and phonetic features are shallow, but the extent of nuance is unclear .
Approach: a new study evaluates contextual syntactic and semantic features in transformer-based speech language models . authors compare SLMs to linguistic competence assessments for large language models.
Outcome: a new study compares SLMs with linguistic competence assessments to assess speech recognition and understanding . the results show that SLM models encode grammatical features more robustly than conceptual ones .
Do self-supervised speech models develop human-like perception biases? (2022.acl-long)

Copied to clipboard

Challenge: Recent advances in speech recognition and representation learning show that self-supervised pretraining is an excellent way of improving performance while reducing the amount of labelled data needed for training.
Approach: They compare the representational spaces of wav2vec, HuBERT and contrastive predictive coding (CPC) with the perceptual spaces of French-speaking and English-speaking human listeners.
Outcome: The proposed models capture fine-grained perceptual phenomena while supervised models are better at capturing coarser, phone-level effects and effects of listeners’ native language on perception.
Unlike “Likely”, “Unlike” is Unlikely: BPE-based Segmentation hurts Morphological Derivations in LLMs (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) use subword vocabularies to process and generate text.
Approach: They find that Large Language Models (LLMs) perform poorly at handling some types of affixations because subwords are marked as initial- or intra-word .
Outcome: The largest models trained on enough data can mitigate this tendency because initial- and intra-word embeddings are aligned; in-context learning also helps when all examples are selected in a consistent way; but only morphological segmentation can achieve a near-perfect accuracy.
Dissecting Contextual Word Embeddings: Architecture and Representation (D18-1)

Copied to clipboard

Challenge: Existing work on learning contextual representations has used LSTM-based biLMs, but there is no reason to believe this is effective.
Approach: They propose to use pre-trained bidirectional language models to learn contextual word embeddings for four NLP tasks and to use them to study the effects of architecture on endtask accuracy.
Outcome: The proposed models outperform word embeddings for four NLP tasks and all learn representations that vary with network depth.
Exploring Layer-wise Representations of English and Chinese Homonymy in Pre-trained Language Models (2025.findings-acl)

Copied to clipboard

Challenge: lexical ambiguity can arise due to the misunderstanding of its multiple senses.
Approach: They propose to use part of speech to examine homonyms in Chinese and English . they find no universal layer depth excels in differentiating homnomial representations .
Outcome: The proposed model improves contextualization of homonym representations in Chinese . the results challenge the simplistic understanding of their inner workings, the authors say .
Radical Allomorphy: Phonological Surface Forms without Phonology (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent work typically frames morphophonology as generating surface forms from abstract underlying representations (URs) this theory-laden assumption is expensive to annotate, especially in low-resource settings.
Approach: a new approach frames morphophonology as generating surface forms from abstract underlying representations by applying phonological rules or constraints.
Outcome: The proposed model removes the need to posit or label URs and lets the model exploit the surface evidence directly.
Morphological Inflection with Phonological Features (2023.acl-short)

Copied to clipboard

Challenge: Recent advances in morphological tasks can be difficult to solve when little training data is available or when generalizing to previously unseen lemmas.
Approach: They propose two methods to manipulate phonemic data to include phonological features instead of characters.
Outcome: The proposed methods yield comparable results to baseline models, with minor improvements in some languages.
Exploring Linguistic Probes for Morphological Inflection (2023.emnlp-main)

Copied to clipboard

Challenge: morphological inflection models typically employ language-independent data splitting algorithms.
Approach: They propose language-specific probes to test aspects of morphological generalization . they use three morphology-distinct languages to test their generalization abilities .
Outcome: The proposed language-specific probes are used to test morphological generalization abilities on three distinct languages.
Encoding of lexical tone in self-supervised models of spoken language (2024.naacl-long)

Copied to clipboard

Challenge: Existing research on representations of phonetic and phonological information has focused on segmental features such as phonemes.
Approach: They propose to analyze the tone encoding capabilities of self-supervised Spoken Language Models, using Mandarin and Vietnamese as case studies.
Outcome: The proposed models encode lexical tone even when trained on non-tonal languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations