Skip to Main content Skip to Navigation
Conference papers

Adding new words into a language model using parameters of known words with similar behavior

Luiza Orosanu 1 Denis Jouvet 1
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : This article presents a study on how to automatically add new words into a language model without retraining it or adapting it (which requires a lot of new data). The proposed approach consists in finding a list of similar words for each new word to be added in the language model. Based on a small set of sentences containing the new words and on a set of n-gram counts containing the known words, we search for known words which have the most similar neighbor distribution (of the few preceding and few following neighbor words) to the new words. The similar words are determined through the computation of KL divergences on the distribution of neighbor words. The n-gram parameter values associated to the similar words are then used to define the n-gram parameter values of the new words. In the context of speech recognition, the performance assessment on a LVCSR task shows the benefit of the proposed approach.
Document type :
Conference papers
Complete list of metadata

Cited literature [25 references]  Display  Hide  Download
Contributor : Denis Jouvet Connect in order to contact the contributor
Submitted on : Thursday, August 13, 2015 - 11:22:25 AM
Last modification on : Saturday, October 16, 2021 - 11:26:09 AM
Long-term archiving on: : Saturday, November 14, 2015 - 10:15:31 AM


Files produced by the author(s)


  • HAL Id : hal-01184194, version 1



Luiza Orosanu, Denis Jouvet. Adding new words into a language model using parameters of known words with similar behavior. International Conference on Natural Language and Speech Processing, Oct 2015, Alger, Algeria. ⟨hal-01184194⟩



Les métriques sont temporairement indisponibles