Joint Learning of Correlated Sequence Labeling Tasks Using Bidirectional Recurrent Neural Networks

Vardaan Pahuja, Anirban Laha, Shachar Mirkin, Vikas Raykar, Lili Kotlerman, Guy Lev


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.


 DOI: 10.21437/Interspeech.2017-1247

Cite as: Pahuja, V., Laha, A., Mirkin, S., Raykar, V., Kotlerman, L., Lev, G. (2017) Joint Learning of Correlated Sequence Labeling Tasks Using Bidirectional Recurrent Neural Networks. Proc. Interspeech 2017, 548-552, DOI: 10.21437/Interspeech.2017-1247.


@inproceedings{Pahuja2017,
  author={Vardaan Pahuja and Anirban Laha and Shachar Mirkin and Vikas Raykar and Lili Kotlerman and Guy Lev},
  title={Joint Learning of Correlated Sequence Labeling Tasks Using Bidirectional Recurrent Neural Networks},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={548--552},
  doi={10.21437/Interspeech.2017-1247},
  url={http://dx.doi.org/10.21437/Interspeech.2017-1247}
}