2026-04-14T02:41:02Zhttps://recercat.cat/oai/request

oai:recercat.cat:10230/327042025-12-19T22:59:31Zcom_2072_6col_2072_452952

00925njm 22002777a 4500 dc Boleda, Gemma author Gupta, Abhijeet author Baroni, Marco author Padó, Sebastian author 2017-08-25T17:17:14Z 2017-08-25T17:17:14Z 2015 Distributional methods have proven to excel at capturing fuzzy, graded aspects of meaning (Italy is more similar to Spain than to Germany). In contrast, it is difficult to extract the values of more specific attributes of word referents from distributional representations, attributes of the kind typically found in structured knowledge bases (Italy has 60 million inhabitants). In this paper, we pursue the hypothesis that distributional vectors also implicitly encode referential attributes. We show that a standard supervised regression model is in fact sufficient to retrieve such attributes to a reasonable degree of accuracy: When evaluated on the prediction of both categorical and numeric attributes of countries and cities, the model consistently reduces baseline error by 30%, and is not far from the upper bound. Further analysis suggests that our model is able to “objectify” distributional representations for entities, anchoring them more firmly in the external world in measurable ways. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 655577 (LOVe); ERC 2011 Starting Independent Research Grant n. 283554 (COMPOSES); DFG (SFB 732, Project D10); and Spanish MINECO (grant FFI2013-41301-P). Reference Distributed representations Semantics Computational semantics Computational Linguistics Natural Language Processing Distributional vectors encode referential attributes