Abstract
Sentence embeddings provide vector representations for sentences and short texts, enabling the capture of contextual and semantic meaning for different applications. However, the diversity of sentence embedding techniques poses a challenge, in terms of choosing the model best suited for the downstream task. As such, meta-embeddings study different techniques for combining embeddings from multiple sources. In this paper, we propose CINCE, a principled meta-embedding framework for aggregating various semantic information, captured by different embeddings techniques, via multiple component analysis strategies. Experiments on SentEval benchmark exhibit improved performance for semantic understanding and text classification, compared to existing approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Andrew, G., Arora, R., Bilmes, J., Livescu, K.: Deep canonical correlation analysis. In: International Conference on Machine Learning (ICML), pp. 1247–1255 (2013)
Artetxe, M., Schwenk, H.: Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond. Trans. Assoc. Comput. Linguist. 7, 597–610 (2019)
Assem, H., Dutta, S., Burgin, E.: DTAFA: decoupled training architecture for efficient FAQ retrieval. In: Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pp. 423–430 (2021)
Bao, C., Bollegala, D.: Learning word meta-embeddings by autoencoding. In: Conference on Computational Linguistics (COLING), pp. 1650–1661 (2018)
Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135–146 (2017)
Cer, D., et al.: Universal Sentence Encoder, arXiv preprint arXiv:1803.11175 (2018)
Chelba, C., et al.: One billion word benchmark for measuring progress in statistical language modeling. In: Conference of the International Speech Communication Association (INTERSPEECH), pp. 2635–2639 (2014)
Chen, W., Sheng, M., Mao, J., Sheng, W.: Investigating word meta-embeddings by disentangling common and individual information. IEEE Access 8, 11692–11699 (2020)
Coates, J.N., Bollegala, D.: Frustratingly easy meta-embedding - computing meta-embeddings by averaging source word embeddings. In: North American Chapter of the Association for Computational Linguistics (NAACL-HLT), pp. 194–198 (2018)
Comon, P.: Independent component analysis - a new concept? Signal Process. 36, 287–314 (1994)
Conneau, A., Kiela, D.: SentEval: an evaluation toolkit for universal sentence representations. In: International Conference on Language Resources and Evaluation (LREC), pp. 1699–1704 (2018)
Conneau, A., Kiela, D., Schwenk, H., Barrault, L., Borders, A.: Supervised learning of universal sentence representations from natural language inference data. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 670–680 (2017)
Conneau, A., Kruszewski, G., Lample, G., Barrault, L., Baroni, M.: What you can cram into a single \$&!#* vector: probing sentence embeddings for linguistic properties. In: Annual Meeting of the Association for Computational Linguistics (ACL), pp. 2126–2136 (2018)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (NAACL-HLT), pp. 4171–4186 (2019)
Dutta, S.: “Alignment is All You Need”: analyzing cross-lingual text similarity for domain-specific applications. In: The Web Conference - Workshop on Cross-lingual Event-centric Open Analytics, pp. 85–92 (2021)
Goswami, K., Dutta, S., Assem, H., Fransen, T., McCrae, J.: Cross-lingual sentence embedding using multi-task learning. In: Empirical Methods in Natural Language Processing (EMNLP) (2021)
Hazem, A., Hernandez, N.: Meta-embedding sentence representation for textual similarity. In: Recent Advances in Natural Language Processing (RANLP), pp. 465–473 (2019)
Hirota, W., Suhara, Y., Golshan, B., Tan, W.C.: EMU: enhancing multilingual sentence embeddings with semantic specialization. In: AAAI Conference on Artificial Intelligence (AAAI), pp. 7935–7943 (2020)
Hotelling, H.: Analysis of a complex of statistical variables into principal components. J. Educ. Psychol. 24(417–441), 498–520 (1933)
Hotelling, H.: Relations between two sets of variates. Biometrika 28(3–4), 321–377 (1936)
Hyvärinen, A., Oja, E.: Independent component analysis: algorithms and applications. Neural Netw. 13(4–5), 411–430 (2000)
Jutten, C., Hérault, J.: Blind separation of sources, Part I: an adaptive algorithm based on neuromimetic architecture. Signal Process. 24, 1–10 (1991)
Kettenring, J.R.: Canonical analysis of several sets of variables. Biometrika 58, 433–451 (1971)
Kiela, D., Wang, C., Cho, K.: Dynamic meta-embeddings for improved sentence representations. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1466–1477 (2018)
Knapp, T.R.: Canonical correlation analysis: a general parametric significance-testing system. Psychol. Bull. 85(2), 410–416 (1978)
Kornblith, S., Norouzi, M., Lee, H., Hinton, G.: Similarity of neural network representations revisited. In: International Conference on Machine Learning (ICML), pp. 3519–3529 (2019)
Lample, G., Conneau, A.: Cross-lingual language model pretraining. In: Conference on Neural Information Processing Systems (NIPS), pp. 1–11 (2019)
Lange, L., Adel, H., Strötgen, J., Klakow, D.: Adversarial learning of feature-based meta-embeddings (2020). arXiv:2010.12305
Li, B., Zhou, H., He, J., Wang, M., Yang, Y., Li, L.: On the sentence embeddings from pre-trained language models. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 9119–9130 (2020)
Lin, Z., et al.: A structured self-attentive sentence embedding. In: International Conference on Learning Representations (ICLR), pp. 1–15 (2017)
Mika, S., Schölkopf, B., Smola, A., Müller, K.R., Scholz, M., Rätsch, G.: Kernel PCA and de-noising in feature spaces. In: Conference on Neural Information Processing Systems (NIPS), pp. 536–542 (1998)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Conference on Neural Information Processing Systems (NIPS), pp. 3111–3119 (2013)
O’Neill, J., Bollegala, D.: Meta-embedding as auxiliary task regularization. In: European Conference on Artificial Intelligence (ECAI), pp. 2124–2131 (2020)
Patel, R.N., Burgin, E., Assem, H., Dutta, S.: Efficient multi-lingual sentence classification framework with sentence meta encoders. In: IEEE International Conference on Big Data (2021)
Pearson, K.: On lines and planes of closest fit to systems of points in space. Phil. Mag. 2(11), 559–572 (1901)
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)
Poerner, N., Waltinger, U., Schütze, H.: Sentence meta-embeddings for unsupervised semantic textual similarity. In: Annual Meeting of the Association for Computational Linguistics (ACL), pp. 7027–7034 (2020)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 3982–3992 (2019)
Schölkopf, B.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10(5), 1299–1319 (1998)
Senel, L.K., Utlu, I., Yucesoy, V., Koc, A., Cukur, T.: Semantic structure and interpretability of word embeddings. IEEE/ACM Trans. Audio Speech Lang. Process. 26(10), 1769–1779 (2018)
Shi, X.: Nonlinear ICA, pp. 97–112. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-11347-5_5
Sørensen, M., Kanatsoulis, C.I., Sidiropoulos, N.D.: Generalized canonical correlation analysis: a subspace intersection approach. arXiv:2003.11205 (2020)
Tsatsishvilil, V., Cong, F., Toiviainen, P., Ristaniemil, T.: Combining PCA and multiset CCA for dimension reduction when group ICA is applied to decompose naturalistic fMRI data. In: International Joint Conference on Neural Networks (IJCNN), pp. 1–6 (2015)
Wieting, J., Gimpel, K.: ParaNMT-50M: pushing the limits of paraphrastic sentence embeddings with millions of machine translations. In: Annual Meeting of the Association for Computational Linguistics (ACL), pp. 451–462 (2018)
Wieting, J., Kiela, D.: No Training required: exploring random encoders for sentence classification. In: International Conference on Learning Representations (ICLR), pp. 1–16 (2019)
Yin, W., Schütze, H.: Learning word meta-embeddings. In: Annual Meeting of the Association for Computational Linguistics (ACL), pp. 1351–1360 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dutta, S., Assem, H. (2022). Enhanced Sentence Meta-Embeddings for Textual Understanding. In: Hagen, M., et al. Advances in Information Retrieval. ECIR 2022. Lecture Notes in Computer Science, vol 13186. Springer, Cham. https://doi.org/10.1007/978-3-030-99739-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-99739-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-99738-0
Online ISBN: 978-3-030-99739-7
eBook Packages: Computer ScienceComputer Science (R0)