mlsanityData to 7 Oct 2026

PWESuite: Phonetic Word Embeddings and Tasks They Facilitate

arXiv 2304.02541 ↗First posted 5 Apr 2023cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Mapping words into a fixed-dimensional vector space is the backbone of modern NLP. While most word embedding methods successfully encode semantic information, they overlook phonetic information that is crucial for many tasks. We develop three methods that use articulatory features to build phonetically informed word embeddings. To address the inconsistent evaluation of existing phonetic word embedding methods, we also contribute a task suite to fairly evaluate past, current, and future methods. We evaluate both (1) intrinsic aspects of phonetic word embeddings, such as word retrieval and correlation with sound similarity, and (2) extrinsic performance on tasks such as rhyme and cognate detection and sound analogies. We hope our task suite will promote reproducibility and inspire future phonetic embedding research.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 27 of its 72 references that are in the map. First posted on arXiv 5 Apr 2023.

Builds on

27 of 72 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  6. 2014Distributed Representations of Sentences and Documentscited by 677
  7. 2019CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Datacited by 544
  8. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  9. 2018Learning Word Vectors for 157 Languagescited by 279
  10. 2016Diachronic Word Embeddings Reveal Statistical Laws of Semantic Changecited by 219
  11. 2017BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languagescited by 52
  12. 2018From Word to Sense Embeddings: A Survey on Vector Representations of Meaningcited by 49
15 more
  1. 2019Word Embeddings: A Surveycited by 45
  2. 2018A Survey of Word Embeddings Evaluation Methodscited by 26
  3. 2018Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representationscited by 18
  4. 2020Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoodscited by 17
  5. 2020Multilingual Jointly Trained Acoustic and Written Word Embeddingscited by 16
  6. 2019Keyphrase Extraction from Disaster-related Tweetscited by 12
  7. 2022Don't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Poolingcited by 12
  8. 2018Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrievalcited by 11
  9. 2021Quantifying Cognitive Factors in Lexical Declinecited by 8
  10. 2018Chinese Poetry Generation with a Working Memory Modelcited by 7
  11. 2021Phonetic Word Embeddingscited by 7
  12. 2021Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learningcited by 6
  13. 2021SIGTYP 2021 Shared Task: Robust Spoken Language Identificationcited by 5
  14. 2022Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)cited by 5
  15. 2019Learning Joint Acoustic-Phonetic Word Embeddingscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 3.

6 papers.

  1. 2026[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmeticcited by 11
  2. 2026Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspacescited by 7
  3. 2024PolyIPA -- Multilingual Phoneme-to-Grapheme Conversion Modelcited by 4
  4. 2025Cross-Lingual IPA Contrastive Learning for Zero-Shot NERcited by 1
  5. 2025The Cognate Data Bottleneck in Language Phylogeneticscited by 0
  6. 2026PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translationcited by 0