Publication detail

A Fast Re-scoring Strategy to Capture Long-Distance Dependencies

DEORAS, A. MIKOLOV, T. CHURCH, K.

Original Title

A Fast Re-scoring Strategy to Capture Long-Distance Dependencies

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

The paper describes novel approach to lattice rescoring with complex lanaguage models with long-distance dependencies, such as recurrent neural network language models.

Keywords

language model, re-scoring strategy, recurrent neural network

Authors

DEORAS, A.; MIKOLOV, T.; CHURCH, K.

RIV year

2011

Released

27. 7. 2011

Publisher

Association for Computational Linguistics

Location

Edinburgh

ISBN

978-1-937284-11-4

Book

Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing July 2011 Edinburgh, Scotland, UK

Pages from

1116

Pages to

1127

Pages count

12

URL

https://www.fit.vut.cz/research/publication/9687/

BibTex

@inproceedings{BUT76392,
  author="Anoop {Deoras} and Tomáš {Mikolov} and Kenneth {Church}",
  title="A Fast Re-scoring Strategy to Capture Long-Distance Dependencies",
  booktitle="Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing July 2011 Edinburgh, Scotland, UK",
  year="2011",
  pages="1116--1127",
  publisher="Association for Computational Linguistics",
  address="Edinburgh",
  isbn="978-1-937284-11-4",
  url="https://www.fit.vut.cz/research/publication/9687/"
}