Improved models for automatic punctuation prediction for spoken and written text

@inproceedings{Ueffing2013ImprovedMF,
  title={Improved models for automatic punctuation prediction for spoken and written text},
  author={Nicola Ueffing and Maximilian Bisani and Paul Vozila},
  booktitle={INTERSPEECH},
  year={2013}
}
This paper presents improved models for the automatic prediction of punctuation marks in written or spoken text. Various kinds of textual features are combined using Conditional Random Fields. These features include language model scores, token n-grams, sentence length, and syntactic information extracted from parse trees. The resulting models are evaluated on several different tasks, ranging from formal newspaper text to informal, dictated messages and documents, and from written text to… CONTINUE READING

Similar Papers

Tables and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 25 CITATIONS

Experiments in Character-Level Neural Network Models for Punctuation

VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

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

  • INTERSPEECH
  • 2017
VIEW 5 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Empirical Evaluation and Combination of Punctuation Prediction Models Applied to Broadcast News

  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
VIEW 3 EXCERPTS
CITES BACKGROUND

Self-attention Based Model for Punctuation Prediction Using Word and Speech Embeddings

  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
VIEW 2 EXCERPTS
CITES BACKGROUND

A Hybrid Deep Learning Architecture for Sentence Unit Detection

  • 2018 International Conference on Asian Language Processing (IALP)
  • 2018

Investigating for Punctuation Prediction in Chinese Speech Transcriptions

  • 2018 International Conference on Asian Language Processing (IALP)
  • 2018
VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 13 REFERENCES