Sound Analogies with Phoneme Embeddings

@inproceedings{Silfverberg2017SoundAW,
  title={Sound Analogies with Phoneme Embeddings},
  author={Miikka Silfverberg and Lingshuang Mao and Mans Hulden},
  year={2017}
}
Vector space models of words in NLP— word embeddings—have been recently shown to reliably encode semantic information, offering capabilities such as solving proportional analogy tasks such as man:woman::king:queen. We study how well these distributional properties carry over to similarly learned phoneme embeddings, and whether phoneme vector spaces align… CONTINUE READING