Chen, O., Ragni, A. orcid.org/0000-0003-0634-4456, Gales, M. et al. (1 more author) (2018) Active memory networks for language modeling. In: Proceedings of Interspeech 2018. Interspeech 2018, 02-06 Sep 2018, Hyderabad, India. International Speech Communication Association (ISCA) , pp. 3338-3342.
Abstract
Making predictions of the following word given the back history of words may be challenging without meta-information such as the topic. Standard neural network language models have an implicit representation of the topic via the back history of words. In this work a more explicit form of topic representation is used via an attention mechanism. Though this makes use of the same information as the standard model, it allows parameters of the network to focus on different aspects of the task. The attention model provides a form of topic representation that is automatically learned from the data. Whereas the recurrent model deals with the (conditional) history representation. The combined model is expected to reduce the stress on the standard model to handle multiple aspects. Experiments were conducted on the Penn Tree Bank and BBC Multi-Genre Broadcast News (MGB) corpora, where the proposed approach outperforms standard forms of recurrent models in perplexity. Finally, N-best list rescoring for speech recognition in the MGB3 task shows word error rate improvements over comparable standard form of recurrent models.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2018 ISCA. Reproduced in accordance with the publisher's self-archiving policy. |
Keywords: | language model; recurrent neural network; memory networks; attention; speech recognition; ASR |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 21 Nov 2019 12:15 |
Last Modified: | 21 Nov 2019 12:15 |
Status: | Published |
Publisher: | International Speech Communication Association (ISCA) |
Refereed: | Yes |
Identification Number: | 10.21437/interspeech.2018-78 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:152764 |