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

English Title

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

Type

conference paper

Language

en

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.

English 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

RIV year

2011

Released

27.07.2011

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

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

1116

Pages to

1127

Pages count

12

URL

Documents

BibTex


@inproceedings{BUT76392,
  author="Anoop {Deoras} and Tomáš {Mikolov} and Kenneth {Church}",
  title="A Fast Re-scoring Strategy to Capture Long-Distance Dependencies",
  annote="The paper describes novel approach to lattice rescoring with complex lanaguage
models with long-distance dependencies, such as recurrent neural network language
models.",
  address="Association for Computational Linguistics",
  booktitle="Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing July 2011 Edinburgh, Scotland, UK",
  chapter="76392",
  edition="NEUVEDEN",
  howpublished="print",
  institution="Association for Computational Linguistics",
  year="2011",
  month="july",
  pages="1116--1127",
  publisher="Association for Computational Linguistics",
  type="conference paper"
}