Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks
This addresses the need for well-formatted text in NLP applications from ASR output, but it is incremental as it builds on existing sequence labeling methods.
The paper tackles the problem of adding punctuation and capitalization to ASR output by proposing a joint modeling technique using bidirectional recurrent neural networks, which improves performance for both tasks.
The stream of words produced by Automatic Speech Recognition (ASR) systems is typically devoid of punctuations and formatting. Most natural language processing applications expect segmented and well-formatted texts as input, which is not available in ASR output. This paper proposes a novel technique of jointly modeling multiple correlated tasks such as punctuation and capitalization using bidirectional recurrent neural networks, which leads to improved performance for each of these tasks. This method could be extended for joint modeling of any other correlated sequence labeling tasks.