國立虎尾科技大學 |

Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding./
Author:	Kiros, Jamie Ryan.
Description:	1 online resource (155 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
Contained By:	Dissertation Abstracts International79-12B(E).
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9780438187375

Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding.
Kiros, Jamie Ryan.

Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding. - 1 online resource (155 pages)

Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.

Thesis (Ph.D.)--University of Toronto (Canada), 2018.

Includes bibliographical references

In this thesis we introduce conditional neural language models based on log-bilinear and recurrent neural networks with applications to multimodal learning and natural language understanding. We first introduce a LSTM encoder for learning visual-semantic embeddings for ranking the relevance of text to images in a joint embedding space. Next we introduce three log-bilinear models for generating image descriptions that integrate both additive and multiplicative interactions. Beyond image conditioning, we describe a multiplicative conditional neural language model for learning distributed representations of attributes and meta data. Our model allows for contextual word relatedness comparisons through decompositions of a word embedding tensor. Finally we show how we can abstract the skip-gram model for learning word representations to a conditional recurrent neural language model for unsupervised learning of sentence representations. We introduce a family of models called contextual encoder-decoders and demonstrate how our models can be used to induce generic sentence representations as well as unaligned generation of short stories conditioned on images. This thesis closes by highlighting several open areas of future work.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780438187375Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding.
LDR:02495ntm a2200325Ki 4500 001 916640
005 20180927111920.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780438187375
035 $a (MiAaPQ)AAI10747308
035 $a (MiAaPQ)toronto:17287
035 $a AAI10747308
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Kiros, Jamie Ryan. $3 1190437
245 1 0 $a Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding.
264 0 $c 2018
300 $a 1 online resource (155 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
500 $a Advisers: Richard Zemel; Ruslan Salakhutdinov.
502 $a Thesis (Ph.D.)--University of Toronto (Canada), 2018.
504 $a Includes bibliographical references
520 $a In this thesis we introduce conditional neural language models based on log-bilinear and recurrent neural networks with applications to multimodal learning and natural language understanding. We first introduce a LSTM encoder for learning visual-semantic embeddings for ranking the relevance of text to images in a joint embedding space. Next we introduce three log-bilinear models for generating image descriptions that integrate both additive and multiplicative interactions. Beyond image conditioning, we describe a multiplicative conditional neural language model for learning distributed representations of attributes and meta data. Our model allows for contextual word relatedness comparisons through decompositions of a word embedding tensor. Finally we show how we can abstract the skip-gram model for learning word representations to a conditional recurrent neural language model for unsupervised learning of sentence representations. We introduce a family of models called contextual encoder-decoders and demonstrate how our models can be used to induce generic sentence representations as well as unaligned generation of short stories conditioned on images. This thesis closes by highlighting several open areas of future work.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Toronto (Canada). $b Computer Science. $3 845521
773 0 $t Dissertation Abstracts International $g 79-12B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10747308 $z click for full text (PQDT)