Přístupnostní navigace
E-application
Search Search Close
Publication detail
BENEŠ, K. KESIRAJU, S. BURGET, L.
Original Title
i-vectors in language modeling: An efficient way of domain adaptation for feed-forward models
Type
conference paper
Language
English
Original Abstract
We show an effective way of adding context information to shallow neural language models. We propose to use Subspace Multinomial Model (SMM) for context modeling and we add the extracted i-vectors in a computationally efficient way. By adding this information, we shrink the gap between shallow feed-forward network and an LSTM from 65 to 31 points of perplexity on the Wikitext-2 corpus (in the case of neural 5-gram model). Furthermore, we show that SMM i-vectors are suitable for domain adaptation and a very small amount of adaptation data (e.g. endmost 5% of a Wikipedia article) brings a substantial improvement. Our proposed changes are compatible with most optimization techniques used for shallow feedforward LMs.
Keywords
language modeling, feed-forward models, subspace multinomial model, domain adaptation
Authors
BENEŠ, K.; KESIRAJU, S.; BURGET, L.
Released
2. 9. 2018
Publisher
International Speech Communication Association
Location
Hyderabad
ISBN
1990-9772
Periodical
Proceedings of Interspeech
Year of study
2018
Number
9
State
French Republic
Pages from
3383
Pages to
3387
Pages count
5
URL
https://www.isca-speech.org/archive/Interspeech_2018/abstracts/1070.html
BibTex
@inproceedings{BUT155102, author="Karel {Beneš} and Santosh {Kesiraju} and Lukáš {Burget}", title="i-vectors in language modeling: An efficient way of domain adaptation for feed-forward models", booktitle="Proceedings of Interspeech 2018", year="2018", journal="Proceedings of Interspeech", volume="2018", number="9", pages="3383--3387", publisher="International Speech Communication Association", address="Hyderabad", doi="10.21437/Interspeech.2018-1070", issn="1990-9772", url="https://www.isca-speech.org/archive/Interspeech_2018/abstracts/1070.html" }