Punctuation causes problems in result presentation and confuses natural language processing algorithms. An ASR system usually does not predict any punctuation or capitalization. We train two variants of Deep Neural Network (DNN) sequence labelling models.
An ASR system usually does not predict any punctuation or capitalization.
Lack of punctuation causes problems in result presentation and confuses both
the human reader andoff-the-shelf natural language processing algorithms. To
overcome these limitations, we train two variants of Deep Neural Network (DNN)
sequence labelling models - a Bidirectional Long Short-Term Memory (BLSTM) and
a Convolutional Neural Network (CNN), to predict the punctuation. The models
are trained on the Fisher corpus which includes punctuation annotation. In our
experiments, we combine time-aligned and punctuated Fisher corpus transcripts
using a sequence alignment algorithm. The neural networks are trained on Common
Web Crawl GloVe embedding of the words in Fisher transcripts aligned with
conversation side indicators and word time infomation. The CNNs yield a better
precision and BLSTMs tend to have better recall. While BLSTMs make fewer
mistakes overall, the punctuation predicted by the CNN is more accurate -
especially in the case of question marks. Our results constitute significant
evidence that the distribution of words in time, as well as pre-trained
embeddings, can be useful in the punctuation prediction task.