@conference{403,
  keywords = {Embeddings, Hyper-parameter, text classification, Word2Vec},
  author = {Nuette Heyns and Etienne Barnard},
  title = {Optimising word embeddings for recognised multilingual speech},
  abstract = {Word embeddings are widely used in natural language processing (NLP) tasks. Most work on word embeddings focuses on monolingual languages with large available datasets. For embeddings to be useful in a multilingual environment, as in South Africa, the training techniques have to be adjusted to cater for a) multiple languages, b) smaller datasets and c) the occurrence of code-switching. One of the biggest roadblocks is to obtain datasets that include examples of natural code-switching, since code switching is generally avoided in written material. A solution to this problem is to use speech recognised data. Embedding packages like Word2Vec and GloVe have default hyper-parameter settings that are usually optimised for training on large datasets and evaluation on analogy tasks. When using embeddings for problems such as text classification in our multilingual environment, the hyper-parameters have to be optimised for the specific data and task. We investigate the importance of optimising relevant hyper-parameters for training word embeddings with speech recognised data, where code-switching occurs, and evaluate against the real-world problem of classifying radio and television recordings with code switching. We compare these models with a bag of words baseline model as well as a pre-trained GloVe model.},
  year = {2020},
  journal = {Southern African Conference for Artificial Intelligence Research},
  chapter = {102-116},
  month = {22/02/2021 - 26/02/2021},
  address = {South Africa},
  isbn = {978-0-620-89373-2},
  url = {https://sacair.org.za/proceedings/},
}