Paraphrastic language models and combination with neural network language models
MetadataShow full item record
Liu, X., Gales, M., & Woodland, P. (2013). Paraphrastic language models and combination with neural network language models. IEEE ICASSP2013, 8421-8425. https://doi.org/10.1109/ICASSP.2013.6639308
In natural languages multiple word sequences can represent the same underlying meaning. Only modelling the observed surface word sequence can result in poor context coverage, for example, when using n-gram language models (LM). To handle this issue, paraphrastic LMs were proposed in previous research and successfully applied to a US English conversational telephone speech transcription task. In order to exploit the complementary characteristics of paraphrastic LMs and neural network LMs (NNLM), the combination between the two is investigated in this paper. To investigate paraphrastic LMs’ generalization ability to other languages, experiments are conducted on a Mandarin Chinese broadcast speech transcription task. Using a paraphrastic multi-level LM modelling both word and phrase sequences, signiﬁcant error rate reductions of 0.9% absolute (9% relative) and 0.5% absolute (5% relative) were obtained over the baseline n-gram and NNLM systems respectively, after a combination with word and phrase level NNLMs.
language model, paraphrase, speech recognition
The research leading to these results was supported by EPSRC Programme Grant EP/I031022/1 (Natural Speech Technology)
External DOI: https://doi.org/10.1109/ICASSP.2013.6639308
This record's URL: https://www.repository.cam.ac.uk/handle/1810/245536