# PWESuite: Phonetic Word Embeddings and Tasks They Facilitate

arXiv: https://arxiv.org/abs/2304.02541 · HTML: https://mlsanity.com/paper/2304.02541/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 72 references that are in the map.
- First posted on arXiv 5 Apr 2023.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data](https://mlsanity.com/paper/1911.00359/) (2019)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Learning Word Vectors for 157 Languages](https://mlsanity.com/paper/1802.06893/) (2018)
- [Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change](https://mlsanity.com/paper/1605.09096/) (2016)
- [BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages](https://mlsanity.com/paper/1710.02187/) (2017)
- [From Word to Sense Embeddings: A Survey on Vector Representations of Meaning](https://mlsanity.com/paper/1805.04032/) (2018)
- [Word Embeddings: A Survey](https://mlsanity.com/paper/1901.09069/) (2019)
- [A Survey of Word Embeddings Evaluation Methods](https://mlsanity.com/paper/1801.09536/) (2018)
- [Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations](https://mlsanity.com/paper/1808.09500/) (2018)
- [Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods](https://mlsanity.com/paper/2001.07740/) (2020)
- [Multilingual Jointly Trained Acoustic and Written Word Embeddings](https://mlsanity.com/paper/2006.14007/) (2020)
- [Keyphrase Extraction from Disaster-related Tweets](https://mlsanity.com/paper/1910.07897/) (2019)
- [Don't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling](https://mlsanity.com/paper/2209.05972/) (2022)
- [Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrieval](https://mlsanity.com/paper/1807.08089/) (2018)
- [Quantifying Cognitive Factors in Lexical Decline](https://mlsanity.com/paper/2110.05775/) (2021)
- [Chinese Poetry Generation with a Working Memory Model](https://mlsanity.com/paper/1809.04306/) (2018)
- [Phonetic Word Embeddings](https://mlsanity.com/paper/2109.14796/) (2021)
- [Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning](https://mlsanity.com/paper/2104.10357/) (2021)
- [SIGTYP 2021 Shared Task: Robust Spoken Language Identification](https://mlsanity.com/paper/2106.03895/) (2021)
- [Unify and Conquer: How Phonetic Feature Representation Affects Polyglot Text-To-Speech (TTS)](https://mlsanity.com/paper/2207.01547/) (2022)
- [Learning Joint Acoustic-Phonetic Word Embeddings](https://mlsanity.com/paper/1908.00493/) (2019)

## Built on by (most cited first, 6 of 6)

- [[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic](https://mlsanity.com/paper/2602.18899/) (2026)
- [Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces](https://mlsanity.com/paper/2603.12642/) (2026)
- [PolyIPA -- Multilingual Phoneme-to-Grapheme Conversion Model](https://mlsanity.com/paper/2412.09102/) (2024)
- [Cross-Lingual IPA Contrastive Learning for Zero-Shot NER](https://mlsanity.com/paper/2503.07214/) (2025)
- [The Cognate Data Bottleneck in Language Phylogenetics](https://mlsanity.com/paper/2507.00911/) (2025)
- [PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation](https://mlsanity.com/paper/2606.12911/) (2026)

## 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.