Multi-Stream Long Short-Term Memory Neural Network Language Model

dc.authorid Ebru Arısoy / 0000-0002-8311-3611
dc.contributor.author Saraçlar, Murat
dc.contributor.author Arısoy, Ebru
dc.date.accessioned 2019-02-28T13:04:26Z
dc.date.accessioned 2019-02-28T11:08:17Z
dc.date.available 2019-02-28T13:04:26Z
dc.date.available 2019-02-28T11:08:17Z
dc.date.issued 2015
dc.department Mühendislik Fakültesi, Elektrik Elektronik Mühendisliği Bölümü en_US
dc.description Ebru Arısoy (MEF Author) en_US
dc.description.WoSDocumentType Proceedings Paper
dc.description.WoSIndexDate 2015 en_US
dc.description.WoSPublishedMonth Eylül en_US
dc.description.WoSYOKperiod YÖK - 2015-16 en_US
dc.description.abstract Long Short-Term Memory (LSTM) neural networks are recurrent neural networks that contain memory units that can store contextual information from past inputs for arbitrary amounts of time. A typical LSTM neural network language model is trained by feeding an input sequence. i.e., a stream of words, to the input layer of the network and the output layer predicts the probability of the next word given the past inputs in the sequence. In this paper we introduce a multi-stream LSTM neural network language model where multiple asynchronous input sequences are fed to the network as parallel streams while predicting the output word sequence. For our experiments, we use a sub-word sequence in addition to a word sequence as the input streams, which allows joint training of the LSTM neural network language model using both information sources. en_US
dc.description.woscitationindex Conference Proceedings Citation Index - Science en_US
dc.identifier.citation Arisoy, E., Saraclar, M., (2015). Multi-stream long short-term memory neural network language model. Conference: 16th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2015) Location: Dresden, GERMANY, vol: 1-5. p. 1413-1417. en_US
dc.identifier.endpage 1417 en_US
dc.identifier.scopus 2-s2.0-84959116680
dc.identifier.scopusquality N/A
dc.identifier.startpage 1413 en_US
dc.identifier.uri https://hdl.handle.net/20.500.11779/665
dc.identifier.volume 1_5 en_US
dc.identifier.wos WOS:000380581600296
dc.identifier.wosquality N/A
dc.institutionauthor Arısoy, Ebru
dc.language.iso en en_US
dc.relation.ispartof Conference: 16th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2015) Location: Dresden, GERMANY Date: SEP 06-10, 2015 en_US
dc.relation.publicationcategory Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/closedAccess en_US
dc.subject Long short-term memory en_US
dc.subject Sub-word-based language modeling en_US
dc.subject Language modeling en_US
dc.title Multi-Stream Long Short-Term Memory Neural Network Language Model en_US
dc.type Conference Object en_US

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Multi-Stream Long Short-Term Memory Neural Network Language Model.pdf
Size:
231.92 KB
Format:
Adobe Portable Document Format
Description:
Konferans Dosyası

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
0 B
Format:
Item-specific license agreed upon to submission
Description: