Abstract
Word embedding promises a quantification of the similarity between terms. However, it is not clear to what extent this similarity value can be of practical use for subsequent information access tasks. In particular, which range of similarity values is indicative of the actual term relatedness? We first observe and quantify the uncertainty of word embedding models with respect to the similarity values they generate. Based on this, we introduce a general threshold which effectively filters related terms. We explore the effect of dimensionality on this general threshold by conducting the experiments in different vector dimensions. Our evaluation on four test collections with four relevance scoring models supports the effectiveness of our approach, as the results of the proposed threshold are significantly better than the baseline while being equal to, or statistically indistinguishable from, the optimal results.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
we do not plot all the terms in the model to maintain the readability of the plot.
References
Baroni, M., Dinu, G., Kruszewski, G.: Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors. In: Proceedings of ACL Conference (2014)
Berger, A., Lafferty, J.: Information retrieval as statistical translation. In: Proceedings of SIGIR (1999)
Cuba Gyllensten, A., Sahlgren, M.: Navigating the semantic horizon using relative neighborhood graphs. In: Proceedings of EMNLP, Lisbon, Portugal (2015)
De Vine, L., Zuccon, G., Koopman, B., Sitbon, L., Bruza, P.: Medical semantic similarity with a neural language model. In: Proceedings of CIKM
Erk, K., Padó, S.: Exemplar-based models for word meaning in context. In: Proceedings of ACL (2010)
Ganguly, D., Roy, D., Mitra, M., Jones, G.J.: Word embedding based generalized language model for information retrieval. In: Proceedings of SIGIR (2015)
Grbovic, M., Djuric, N., Radosavljevic, V., Silvestri, F., Bhamidipati, N.: Context-and content-aware embeddings for query rewriting in sponsored search. In: Proceedings of SIGIR (2015)
Karlgren, J., Bohman, M., Ekgren, A., Isheden, G., Kullmann, E., Nilsson, D.: Semantic topology. In: Proceedings of CIKM Conference (2014)
Karlgren, J., Holst, A., Sahlgren, M.: Filaments of meaning in word space. In: Macdonald, C., Ounis, I., Plachouras, V., Ruthven, I., White, R.W. (eds.) ECIR 2008. LNCS, vol. 4956, pp. 531–538. Springer, Heidelberg (2008). doi:10.1007/978-3-540-78646-7_52
Kiela, D., Hill, F., Clark, S.: Specializing word embeddings for similarity or relatedness. In: Proceedings of EMNLP (2015)
Koopman, B., Zuccon, G., Bruza, P., Sitbon, L., Lawley, M.: An evaluation of corpus-driven measures of medical concept similarity for information retrieval. In: Proceedings of CIKM (2012)
Kruszewski, G., Baroni, M.: So similar and yet incompatible: toward automated identification of semantically compatible words. In: Proceedings of NAACL (2015)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)
Mitra, B.: Exploring session context using distributed representations of queries and reformulations. In: Proceedings of SIGIR (2015)
Ponte, J.M., Croft, W.B.: A language modeling approach to information retrieval. In: Proceedings of SIGIR (1998)
Rekabsaz, N., Bierig, R., Ionescu, B., Hanbury, A., Lupu, M.: On the use of statistical semantics for metadata-based social image retrieval. In: Proceedings of CBMI Conference (2015)
Rekabsaz, N., Lupu, M., Hanbury, A.: Generalizing translation models in the probabilistic relevance framework. In: Proceedings of CIKM (2016)
Sakai, T.: Alternatives to bpref. In: Proceedings of SIGIR (2007)
Schnabel, T., Labutov, I., Mimno, D., Joachims, T.: Evaluation methods for unsupervised word embeddings. In: Proceedings of EMNLP (2015)
Severyn, A., Moschitti, A.: Learning to rank short text pairs with convolutional deep neural networks. In: Proceedings of SIGIR (2015)
Tsvetkov, Y., Faruqui, M., Ling, W., Lample, G., Dyer, C.: Evaluation of word vector representations by subspace alignment. In: Proceedings of EMNLP (2015)
Vulić, I., Moens, M.-F.: Monolingual and cross-lingual information retrieval models based on (bilingual) word embeddings. In: Proceedings of SIGIR (2015)
Acknowledgement
This work is funded by: Self-Optimizer (FFG 852624) in the EUROSTARS programme, funded by EUREKA, the BMWFW and the European Union, and ADMIRE (P 25905-N23) by FWF. Thanks to Joni Sayeler and Linus Wretblad for their contributions in the SelfOptimizer project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Rekabsaz, N., Lupu, M., Hanbury, A. (2017). Exploration of a Threshold for Similarity Based on Uncertainty in Word Embedding. In: Jose, J., et al. Advances in Information Retrieval. ECIR 2017. Lecture Notes in Computer Science(), vol 10193. Springer, Cham. https://doi.org/10.1007/978-3-319-56608-5_31
Download citation
DOI: https://doi.org/10.1007/978-3-319-56608-5_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-56607-8
Online ISBN: 978-3-319-56608-5
eBook Packages: Computer ScienceComputer Science (R0)