Name
Title | ||
|---|---|---|
Abin-based ontological framework for low-resourcen-gram smoothing in language modelling |
Abstract | ||
|---|---|---|
In this paper, we introduce a novel method of smoothing language models (LM) based on the semantic information found in ontologies that is especially adapted for limited-resources language modeling. We exploit the latent knowledge of language that is deeply encoded within ontologies. As such, this work examines the potential of using the semantic and syntactic relations between words from the WordNet ontology to generate new plausible contexts for unseen events to simulate a larger corpus. These unseen events are then mixed-up with a baseline Witten-Bell(WB) LM in order to improve its performance both in terms of language model perplexity and automatic speech recognition word error rates. Results indicate a significant reduction in the perplexity of the language model (up to 9.85% relative) all the while reducing word error rate in a statistically significant manner compared to both the original WB LM and baseline Kneser-Ney smoothed language model on the Wall Street Journal-based Continuous Speech Recognition Phase II corpus. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ICASSP.2014.6854537 | Acoustics, Speech and Signal Processing |
Keywords | Field | DocType |
natural language processing,ontologies (artificial intelligence),speech recognition,LM smoothing,Wall Street Journal,WordNet ontology,automatic speech recognition word error rates,baseline WB LM,baseline Witten-Bell LM,bin-based ontological framework,continuous speech recognition phase II corpus,in ontologies,language model perplexity,language model smoothing,limited-resources language modeling,low-resource N-gram smoothing,plausible context generation,semantic relation,syntactic relation,unseen events,word error rate reduction,Language modeling,context modeling,low-resource speech recognition,ontologies | Ontology,Cache language model,Pattern recognition,Computer science,Smoothing,Natural language processing,Artificial intelligence,Gram,Language modelling | Conference |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yacine Benahmed | 1 | 2 | 2.48 |
| Sid-Ahmed Selouani | 2 | 15 | 5.71 |
| Douglas D. O'Shaughnessy | 3 | 0 | 0.34 |