This paper proposes a novel problem setting of selectional preference (SP) between a predicate and its arguments, called as context-sensitive SP (CSP). CSP models the narrative consistency between the predicate and preceding contexts of its arguments, in addition to the conventional SP based on semantic types. Furthermore, we present a novel CSP model that extends the neural SP model (Van de Cruys, 2014) to incorporate contextual information into the distributed representations of arguments. Experimental results demonstrate that the proposed CSP model successfully learns CSP and outperforms the conventional SP model in coreference cluster ranking.
@inproceedings{inoue-etal-2016-modeling, title = "Modeling Context-sensitive Selectional Preference with Distributed Representations", author = "Inoue, Naoya and Matsubayashi, Yuichiroh and Ono, Masayuki and Okazaki, Naoaki and Inui, Kentaro", editor = "Matsumoto, Yuji and Prasad, Rashmi", booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers", month = dec, year = "2016", address = "Osaka, Japan", publisher = "The COLING 2016 Organizing Committee", url = "https://aclanthology.org/C16-1266/", pages = "2829--2838", abstract = "This paper proposes a novel problem setting of selectional preference (SP) between a predicate and its arguments, called as context-sensitive SP (CSP). CSP models the narrative consistency between the predicate and preceding contexts of its arguments, in addition to the conventional SP based on semantic types. Furthermore, we present a novel CSP model that extends the neural SP model (Van de Cruys, 2014) to incorporate contextual information into the distributed representations of arguments. Experimental results demonstrate that the proposed CSP model successfully learns CSP and outperforms the conventional SP model in coreference cluster ranking."}
%0 Conference Proceedings%T Modeling Context-sensitive Selectional Preference with Distributed Representations%A Inoue, Naoya%A Matsubayashi, Yuichiroh%A Ono, Masayuki%A Okazaki, Naoaki%A Inui, Kentaro%Y Matsumoto, Yuji%Y Prasad, Rashmi%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers%D 2016%8 December%I The COLING 2016 Organizing Committee%C Osaka, Japan%F inoue-etal-2016-modeling%X This paper proposes a novel problem setting of selectional preference (SP) between a predicate and its arguments, called as context-sensitive SP (CSP). CSP models the narrative consistency between the predicate and preceding contexts of its arguments, in addition to the conventional SP based on semantic types. Furthermore, we present a novel CSP model that extends the neural SP model (Van de Cruys, 2014) to incorporate contextual information into the distributed representations of arguments. Experimental results demonstrate that the proposed CSP model successfully learns CSP and outperforms the conventional SP model in coreference cluster ranking.%U https://aclanthology.org/C16-1266/%P 2829-2838