Title:
PUNCTUATION MARK DELETE MODEL TRAINING DEVICE, PUNCTUATION MARK DELETE MODEL, AND DETERMINATION DEVICE
Document Type and Number:
WIPO Patent Application WO/2021/215262
Kind Code:
A1
Abstract:
This punctuation mark delete model training device generates, through machine training, a punctuation mark delete model for determining the propriety of a punctuation mark imparted to text obtained by a speech recognition process, the device comprising: a first training data generation unit which generates, on the basis of a first text corpus composed from the text obtained by the speech recognition process, first training data composed of a pair of an input sentence, which is formed by a punctuation mark, a preamble that is a sentence in which the punctuation mark is imparted to the end of the sentence, and postamble that is a sentence immediately after the punctuation mark, and a label that indicates the propriety of imparting the punctuation mark; and a model training unit which updates parameters of the punctuation mark delete model on the basis of an error between the label and a probability obtained by inputting the input sentence of the first training data to the punctuation mark delete model.
Inventors:
KATOU TAKU (JP)
Application Number:
PCT/JP2021/014931
Publication Date:
October 28, 2021
Filing Date:
April 08, 2021
Export Citation:
Assignee:
NTT DOCOMO INC (JP)
International Classes:
G06F16/33; G10L15/16; G10L15/22
Domestic Patent References:
WO2009122779A1 | 2009-10-08 |
Foreign References:
JP2003263190A | 2003-09-19 | |||
JP6605105B1 | 2019-11-13 | |||
JP2001083987A | 2001-03-30 | |||
JPH11126091A | 1999-05-11 | |||
JP2015219480A | 2015-12-07 |
Other References:
SOFUE, SHO ET AL.: "Evaluation of discriminative models in sentence boundary detection of speech recognition results", PROCEEDINGS OF THE 15TH ANNUAL MEETING OF THE ASSOCIATION FOR NATURAL LANGUAGE PROCESSING, 15 March 2009 (2009-03-15), pages 582 - 585
Attorney, Agent or Firm:
HASEGAWA Yoshiki et al. (JP)
Download PDF: