Out-of-Vocabulary Word Probability Estimation using RNN Language Model

Irina Illina 1 Dominique Fohr 1
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : One important issue of speech recognition systems is Out-of Vocabulary words (OOV). These words, often proper nouns or new words, are essential for documents to be transcribed correctly. Thus, they must be integrated in the language model (LM) and the lexicon of the speech recognition system. This article proposes new approaches to OOV proper noun estimation using Recurrent Neural Network Language Model (RNNLM). The proposed approaches are based on the notion of closest in-vocabulary (IV) words (list of brothers) to a given OOV proper noun. The probabilities of these words are used to estimate the probabilities of OOV proper nouns thanks to RNNLM. Three methods for retrieving the relevant list of brothers are studied. The main advantages of the proposed approaches are that the RNNLM is not retrained and the architecture of the RNNLM is kept intact. Experiments on real text data from the website of the Euronews channel show perplexity reductions of about 14% relative compared to baseline RNNLM.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [17 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01623784
Contributor : Dominique Fohr <>
Submitted on : Wednesday, October 25, 2017 - 4:17:04 PM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Document(s) archivé(s) le : Friday, January 26, 2018 - 3:09:09 PM

File

LTC2017_17oct.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01623784, version 1

Citation

Irina Illina, Dominique Fohr. Out-of-Vocabulary Word Probability Estimation using RNN Language Model. 8th Language & Technology Conference, Nov 2017, Poznan, Poland. ⟨hal-01623784⟩

Share

Metrics

Record views

346

Files downloads

559