Abstract
Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we-9*6 propose a Scalable Multilingual Aligned Language Representation (SMALR) that supports many languages with few model parameters without sacrificing downstream task performance. SMALR learns a fixed size language-agnostic representation for most words in a multilingual vocabulary, keeping language-specific features for just a few. We use a masked cross-language modeling loss to align features with context from other languages. Additionally, we propose a cross-lingual consistency module that ensures predictions made for a query and its machine translation are comparable. The effectiveness of SMALR is demonstrated with ten diverse languages, over twice the number supported in vision-language tasks to date. We evaluate on multilingual image-sentence retrieval and outperform prior work by 3–4% with less than 1/5th the training parameters compared to other word embedding methods.
Project page: http://ai.bu.edu/smalr.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aharoni, R., Johnson, M., Firat, O.: Massively multilingual neural machine translation. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), June 2019
Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Antol, S., et al.: VQA: visual question answering. In: The IEEE International Conference on Computer Vision (ICCV) (2015)
Arora, S., Liang, Y., Ma, T.: A simple but tough-to-beat baseline for sentence embeddings. In: International Conference on Learning Representations (ICLR) (2017)
Artetxe, M., Labaka, G., Agirre, E.: Learning principled bilingual mappings of word embeddings while preserving monolingual invariance. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 2289–2294 (2016)
Barrault, L., Bougares, F., Specia, L., Lala, C., Elliott, D., Frank, S.: Findings of the third shared task on multimodal machine translation. In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pp. 304–323 (2018)
Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. (TACL) 5, 135–146 (2017)
Burns, A., Tan, R., Saenko, K., Sclaroff, S., Plummer, B.A.: Language features matter: effective language representations for vision-language tasks. In: The IEEE International Conference on Computer Vision (ICCV) (2019)
Cho, K., van Merrienboer, B., Gülçehre, Ç., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Empirical Methods in Natural Language Processing (EMNLP) (2014)
Conneau, A., Lample, G.: Cross-lingual language model pretraining. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)
Conneau, A., Lample, G., Ranzato, M., Denoyer, L., Jégou, H.: Word translation without parallel data. In: International Conference on Learning Representations (ICLR) (2018)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2009)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805v1 (2018)
Elliott, D., Frank, S., Barrault, L., Bougares, F., Specia, L.: Findings of the second shared task on multimodal machine translation and multilingual image description. arXiv:1710.07177 (2017)
Elliott, D., Frank, S., Sima’an, K., Specia, L.: Multi30k: multilingual English-German image descriptions. arXiv:1605.00459 (2016)
Gella, S., Sennrich, R., Keller, F., Lapata, M.: Image pivoting for learning multilingual multimodal representations. In: Empirical Methods in Natural Language Processing (EMNLP) (2017)
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in Visual Question Answering. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Gu, J., Hassan, H., Devlin, J., Li, V.O.: Universal neural machine translation for extremely low resource languages. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT) (2018)
Gupta, T., Schwing, A., Hoiem, D.: Vico: word embeddings from visual co-occurrences. In: The IEEE International Conference on Computer Vision (ICCV) (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv:1512.03385 (2015)
K, K., Wang, Z., Mayhew, S., Roth, D.: Cross-lingual ability of multilingual bert: an empirical study. arXiv:1912.07840 (2019)
Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferitGame: referring to objects in photographs of natural scenes. In: Empirical Methods in Natural Language Processing (EMNLP) (2014)
Kim, D., Saito, K., Saenko, K., Sclaroff, S., Plummer, B.A.: Mule: multimodal universal language embedding. In: AAAI Conference on Artificial Intelligence (2020)
Klein, B., Lev, G., Sadeh, G., Wolf, L.: Fisher vectors derived from hybrid Gaussian-Laplacian mixture models for image annotation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Krishna, R., et al.: Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. (IJCV) (2017)
Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language. arXiv:1908.03557 (2019)
Li, X., et al.: COCO-CN for cross-lingual image tagging, captioning and retrieval. IEEE Trans. Multimedia (2019)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. arXiv:1908.02265 (2019)
Maćkiewicz, A., Ratajczak, W.: Principal components analysis (PCA). Comput. Geosci. 19(3), 303–342 (1993)
Miyazaki, T., Shimizu, N.: Cross-lingual image caption generation. In: Conference of the Association for Computational Linguistics (ACL) (2016)
Nguyen, D.K., Okatani, T.: Multi-task learning of hierarchical vision-language representation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Pires, T., Schlinger, E., Garrette, D.: How multilingual is multilingual bert? arXiv:1906.01502 (2019)
Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: The IEEE International Conference on Computer Vision (ICCV) (2015)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2015)
Smith, S.L., Turban, D.H.P., Hamblin, S., Hammerla, N.Y.: Offline bilingual word vectors, orthogonal transformations and the inverted softmax. arXiv:1702.03859 (2017)
Su, W., et al.: Vl-BERT: pre-training of generic visual-linguistic representations. arXiv:1908.08530 (2019)
Tan, H., Bansal, M.: Lxmert: learning cross-modality encoder representations from transformers. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2019)
Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems (NeurIPS), pp. 5998–6008 (2017)
Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. IEEE Trans. Pattern Anal. Mach. Intell.(TPAMI) 41(2), 394–407 (2018)
Wehrmann, J., Souza, D.M., Lopes, M.A., Barros, R.C.: Language-agnostic visual-semantic embeddings. In: The IEEE International Conference on Computer Vision (ICCV) (2019)
Wu, S., Dredze, M.: Beto, Bentz, Becas: the surprising cross-lingual effectiveness of Bert. arXiv:1904.09077 (2019)
Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. (TACL) 2, 67–78 (2014)
Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Acknowledgements
This work is funded in part by the NSF, DARPA LwLL, and DARPA XAI grants, including NSF grant 1838193.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Burns, A., Kim, D., Wijaya, D., Saenko, K., Plummer, B.A. (2020). Learning to Scale Multilingual Representations for Vision-Language Tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12349. Springer, Cham. https://doi.org/10.1007/978-3-030-58548-8_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-58548-8_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58547-1
Online ISBN: 978-3-030-58548-8
eBook Packages: Computer ScienceComputer Science (R0)