Skip to main content

2018 | OriginalPaper | Buchkapitel

Generating Chinese Poems from Images Based on Neural Network

verfasst von : Shuo Xing, Xueliang Liu, Richang Hong, Ye Zhao

Erschienen in: Advances in Multimedia Information Processing – PCM 2017

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Chinese classical poetry generation from images is an overwhelmingly challenging work in the field of artificial intelligence. Inspired by recent advances in automatically generating description of an image and Chinese poem generation, in this paper, we present a generative model based on deep recurrent framework that describes images in the form of poems. Our model consists of two parts, one is to extract information according to the semantics presented in images, and the other is to generate each line of the poem incrementally according to the extracted semantic information from the images by a recurrent neural network. Experimental results thoroughly demonstrate the effectiveness of our approach by manual evaluation.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Bernstein, M., Khosla, A., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. IJCV 115, 211–252 (2015)MathSciNetCrossRef Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Bernstein, M., Khosla, A., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. IJCV 115, 211–252 (2015)MathSciNetCrossRef
2.
Zurück zum Zitat Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR, pp. 1602–1605 (2009) Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR, pp. 1602–1605 (2009)
3.
Zurück zum Zitat Kulkarni, G., Premraj, V., Dhar, S., Li, S., Berg, A., Choi, Y., Berg, T.: Baby talk: understanding and generating simple image descriptions. In: CVPR (2011) Kulkarni, G., Premraj, V., Dhar, S., Li, S., Berg, A., Choi, Y., Berg, T.: Baby talk: understanding and generating simple image descriptions. In: CVPR (2011)
4.
Zurück zum Zitat Farhadi, A., Hejrati, M., Sadeghi, M.A., Young, P., Rashtchian, C., Hockenmaier, J., Forsyth, D.: Every picture tells a story: generating sentences for images. In: ECCV (2010)CrossRef Farhadi, A., Hejrati, M., Sadeghi, M.A., Young, P., Rashtchian, C., Hockenmaier, J., Forsyth, D.: Every picture tells a story: generating sentences for images. In: ECCV (2010)CrossRef
5.
Zurück zum Zitat Yao, B.Z., Yang, X., Lin, L., Lee, M.W., Zhu, S.C.: I2T: image parsing to text description. Proc. IEEE 98(8), 1485–1508 (2010)CrossRef Yao, B.Z., Yang, X., Lin, L., Lee, M.W., Zhu, S.C.: I2T: image parsing to text description. Proc. IEEE 98(8), 1485–1508 (2010)CrossRef
6.
Zurück zum Zitat Elliott, D., Keller, F.: Image description using visual dependency representations. In: EMNLP, pp. 1292–1302 (2013) Elliott, D., Keller, F.: Image description using visual dependency representations. In: EMNLP, pp. 1292–1302 (2013)
7.
Zurück zum Zitat Li, S., Kulkarni, G., Berg, T.L., Berg, A.C., Choi, Y.: Composing simple image descriptions using web-scale n-grams. In: CoNLL (2011) Li, S., Kulkarni, G., Berg, T.L., Berg, A.C., Choi, Y.: Composing simple image descriptions using web-scale n-grams. In: CoNLL (2011)
8.
Zurück zum Zitat Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47(1), 853–899 (2013)MathSciNetMATH Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47(1), 853–899 (2013)MathSciNetMATH
9.
Zurück zum Zitat Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. arXiv preprint arXiv:1411.4555 (2014) Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. arXiv preprint arXiv:​1411.​4555 (2014)
10.
Zurück zum Zitat Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015) Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)
11.
Zurück zum Zitat Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A.C., Salakhutdinov, R., Zemel, R.S., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. arXiv preprint arXiv:1502.03044 (2015) Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A.C., Salakhutdinov, R., Zemel, R.S., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. arXiv preprint arXiv:​1502.​03044 (2015)
12.
Zurück zum Zitat Zhang, X., Lapata, M.: Chinese poetry generation with recurrent neural networks. In: EMNLP, pp. 670–680 (2014) Zhang, X., Lapata, M.: Chinese poetry generation with recurrent neural networks. In: EMNLP, pp. 670–680 (2014)
13.
Zurück zum Zitat Wang, Q., Luo, T., Wang, D., Xing, C.: Chinese song iambics generation with neural attention-based model. CoRR, abs/1604.06274 (2016) Wang, Q., Luo, T., Wang, D., Xing, C.: Chinese song iambics generation with neural attention-based model. CoRR, abs/1604.06274 (2016)
14.
Zurück zum Zitat Yi, X., Li, R., Sun, M.: Generating Chinese classical poems with RNN encoder-decoder. CoRR, abs/1604.01537 (2016) Yi, X., Li, R., Sun, M.: Generating Chinese classical poems with RNN encoder-decoder. CoRR, abs/1604.01537 (2016)
15.
Zurück zum Zitat Colton, S., Goodwin, J., Veale, T.: Full FACE poetry generation. In: ICCC, pp. 95–102 (2012) Colton, S., Goodwin, J., Veale, T.: Full FACE poetry generation. In: ICCC, pp. 95–102 (2012)
16.
Zurück zum Zitat Oliveira, H.: Automatic generation of poetry: an overview. Universidade de Coimbra (2009) Oliveira, H.: Automatic generation of poetry: an overview. Universidade de Coimbra (2009)
17.
Zurück zum Zitat Oliveira, H.: Poetryme: a versatile platform for poetry generation. Comput. Creat. Concept Inven. Gen. Intell. 1, 21 (2012) Oliveira, H.: Poetryme: a versatile platform for poetry generation. Comput. Creat. Concept Inven. Gen. Intell. 1, 21 (2012)
18.
Zurück zum Zitat Jiang, L., Zhou, M.: Generating Chinese couplets using a statistical MT approach. In: Proceedings of the 22nd International Conference on Computational Linguistics, pp. 377–384 (2008) Jiang, L., Zhou, M.: Generating Chinese couplets using a statistical MT approach. In: Proceedings of the 22nd International Conference on Computational Linguistics, pp. 377–384 (2008)
19.
Zurück zum Zitat He, J., Zhou, M., Jiang, L.: Generating Chinese classical poems with statistical machine translation models. In: AAAI, pp. 1650–1656 (2012) He, J., Zhou, M., Jiang, L.: Generating Chinese classical poems with statistical machine translation models. In: AAAI, pp. 1650–1656 (2012)
20.
Zurück zum Zitat Zhou, C.L., You, W., Ding, X.: Genetic algorithm and its implementation of automatic generation of Chinese songci. J. Softw. 21(3), 427–437 (2010)CrossRef Zhou, C.L., You, W., Ding, X.: Genetic algorithm and its implementation of automatic generation of Chinese songci. J. Softw. 21(3), 427–437 (2010)CrossRef
21.
Zurück zum Zitat Wang, L.: A Summary of Rhyming Constraints of Chinese Poems (in Chinese). Beijing Press, Beijing (2002) Wang, L.: A Summary of Rhyming Constraints of Chinese Poems (in Chinese). Beijing Press, Beijing (2002)
22.
Zurück zum Zitat Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012) Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)
23.
Zurück zum Zitat Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009) Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)
24.
Zurück zum Zitat Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)CrossRef Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)CrossRef
25.
Zurück zum Zitat Liu, C.W., Lowe, R., Serban, I.V., Noseworthy, M., Charlin, L., Pineau, J.: How not to evaluate your dialogue system: an empirical study of unsupervised evaluation metrics for dialogue response generation. arXiv preprint arXiv:1603.08023 (2016) Liu, C.W., Lowe, R., Serban, I.V., Noseworthy, M., Charlin, L., Pineau, J.: How not to evaluate your dialogue system: an empirical study of unsupervised evaluation metrics for dialogue response generation. arXiv preprint arXiv:​1603.​08023 (2016)
26.
Zurück zum Zitat Wu, Q., Shen, C., Liu, L., Dick, A., van den Hengel, A.: What value do explicit high level concepts have in vision to language problems? In: CVPR (2016) Wu, Q., Shen, C., Liu, L., Dick, A., van den Hengel, A.: What value do explicit high level concepts have in vision to language problems? In: CVPR (2016)
27.
Zurück zum Zitat Hong, R., Yang, Y., Wang, M., Hua, X.-S.: Learning visual semantic relationships for efficient visual retrieval. IEEE Trans. Big Data 1(4), 152–161 (2015)CrossRef Hong, R., Yang, Y., Wang, M., Hua, X.-S.: Learning visual semantic relationships for efficient visual retrieval. IEEE Trans. Big Data 1(4), 152–161 (2015)CrossRef
28.
Zurück zum Zitat Zhang, H., Shang, X., Luan, H.-B., Wang, M., Chua, T.-S.: Learning from collective intelligence: feature learning using social images and tags. TOMCCAP 13(1), 1:1–1:23 (2016)CrossRef Zhang, H., Shang, X., Luan, H.-B., Wang, M., Chua, T.-S.: Learning from collective intelligence: feature learning using social images and tags. TOMCCAP 13(1), 1:1–1:23 (2016)CrossRef
29.
Zurück zum Zitat Zhang, H., Kyaw, Z., Chang, S.-F., Chua, T.-S.: Visual translation embedding network for visual relation detection. In: CVPR (2017) Zhang, H., Kyaw, Z., Chang, S.-F., Chua, T.-S.: Visual translation embedding network for visual relation detection. In: CVPR (2017)
Metadaten
Titel
Generating Chinese Poems from Images Based on Neural Network
verfasst von
Shuo Xing
Xueliang Liu
Richang Hong
Ye Zhao
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-319-77380-3_52

Neuer Inhalt