Automatic Speech Recognition (ASR) systems introduce word errors, which often confuse punctuation prediction models, turning punctuation restoration into a challenging task. These errors usually take the form of homonyms. We show how retrofitting of the word embeddings on the domain-specific data can mitigate ASR errors. Our main contribution is a method for better alignment of homonym embeddings and the validation of the presented method on the punctuation prediction task. We record the absolute improvement in punctuation prediction accuracy between 6.2% (for question marks) to 9% (for periods) when compared with the state-of-the-art model.
@article{arxiv.2004.05985,
title = {Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?},
author = {Łukasz Augustyniak and Piotr Szymanski and Mikołaj Morzy and Piotr Zelasko and Adrian Szymczak and Jan Mizgajski and Yishay Carmiel and Najim Dehak},
journal= {arXiv preprint arXiv:2004.05985},
year = {2020}
}