Abstract
Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a semantically meaningful way, we suggest the use of the Stanford Question Answering Dataset (SQuAD) in an open-domain question answering context, where the first task is to find paragraphs useful for answering a given question. First, we compare the quality of various text-embedding methods on the performance of retrieval and give an extensive empirical comparison on the performance of various non-augmented base embedding with, and without IDF weighting. Our main results are that by training deep residual neural models, specifically for retrieval purposes, can yield significant gains when it is used to augment existing embeddings. We also establish that deeper models are superior to this task. The best base baseline embeddings augmented by our learned neural approach improves the top-1 paragraph recall of the system by \(14\%\).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bengio, Y., Ducharme, R., Vincent, P., Janvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137–1155 (2003)
Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135–146 (2017)
Cao, Q., Ying, Y., Li, P.: Similarity metric learning for face recognition. In: 2013 IEEE International Conference on Computer Vision, pp. 2408–2415 (2013)
Cer, D., et al.: Universal sentence encoder (2018)
Chechik, G., Sharma, V., Shalit, U., Bengio, S.: Large scale online learning of image similarity through ranking. J. Mach. Learn. Res. 11, 1109–1135 (2010)
Chelba, C., et al.: One billion word benchmark for measuring progress in statistical language modeling. Technical report (2013)
Chen, D., Fisch, A., Weston, J., Bordes, A.: Reading wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051 (2017)
Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification, vol. 1, pp. 539–546 (2005)
Conneau, A., Kiela, D., Schwenk, H., Barrault, L., Bordes, A.: Supervised learning of universal sentence representations from natural language inference data. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 670–680 (2017)
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR 2006, pp. 1735–1742 (2006)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Hill, F., Cho, K., Korhonen, A.: Learning distributed representations of sentences from unlabelled data. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1367–1377 (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Iyyer, M., Manjunatha, V., Boyd-Graber, J.L., III, H.D.: Deep unordered composition rivals syntactic methods for text classification. In: ACL, no. 1, pp. 1681–1691 (2015)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kiros, R., et al.: Skip-thought vectors. In: Advances in Neural Information Processing Systems, vol. 28, pp. 3294–3302 (2015)
Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. In: ICML, vol. 32, pp. 1188–1196 (2014)
Lowe, D.G.: Similarity metric learning for a variable-kernel classifier. Neural Comput. 7(1), 72–85 (1995)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, vol. 26, pp. 3111–3119 (2013)
Pagliardini, M., Gupta, P., Jaggi, M.: Unsupervised learning of sentence embeddings using compositional n-gram features. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long Papers), pp. 528–540 (2018)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Perone, C.S., Silveira, R., Paula, T.S.: Evaluation of sentence embeddings in downstream and linguistic probing tasks. arXiv preprint arXiv:1806.06259 (2018)
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., Zettlemoyer, L.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long Papers), pp. 2227–2237 (2018)
Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)
Rücklé, A., Eger, S., Peyrard, M., Gurevych, I.: Concatenated p-mean word embeddings as universal cross-lingual sentence representations. arXiv preprint arXiv:1803.01400 (2018)
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering, pp. 815–823 (2015)
Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: NIPS 2016, pp. 1857–1865 (2016)
Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification, pp. 1988–1996 (2014)
Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: CVPR 2014, pp. 1701–1708 (2014)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30, pp. 5998–6008 (2017)
Wang, J., et al.: Learning fine-grained image similarity with deep ranking, pp. 1386–1393 (2014)
Wang, J., Zhou, F., Wen, S., Liu, X., Lin, Y.: Deep metric learning with angular loss (2017)
Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification, vol. 10, pp. 207–244 (2009)
Xing, E.P., Ng, A.Y., Jordan, M.I., Russell, S.: Distance metric learning, with application to clustering with side-information. In: NIPS 2002, pp. 521–528 (2002)
Yu, A.W., et al.: Qanet: combining local convolution with global self-attention for reading comprehension. arXiv preprint arXiv:1804.09541 (2018)
Acknowledgments
This study used the Google Cloud Computing Platform (GCP) which is supported by Google AI research grant.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Cakaloglu, T., Szegedy, C., Xu, X. (2020). Text Embeddings for Retrieval from a Large Knowledge Base. In: Dalpiaz, F., Zdravkovic, J., Loucopoulos, P. (eds) Research Challenges in Information Science. RCIS 2020. Lecture Notes in Business Information Processing, vol 385. Springer, Cham. https://doi.org/10.1007/978-3-030-50316-1_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-50316-1_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-50315-4
Online ISBN: 978-3-030-50316-1
eBook Packages: Computer ScienceComputer Science (R0)