Temporal Word Analogies: Identifying Lexical Replacement with Diachronic Word Embeddings

DSpace/Manakin Repository

Show simple item record

dc.contributor.author Szymanski, Terrence
dc.date.accessioned 2018-01-11T15:06:41Z
dc.date.available 2018-01-11T15:06:41Z
dc.date.copyright 2017 Association for Computational Linguistics en
dc.date.issued 2017-08-04
dc.identifier.uri http://hdl.handle.net/10197/9166
dc.description.abstract This paper introduces the concept of temporal word analogies: pairs of words which occupy the same semantic space at different points in time. One well-known property of word embeddings is that they are able to effectively model traditional word analogies ("word w1 is to word w2 as word w3 is to word w4") through vector addition. Here, I show that temporal word analogies ("word w1 at time ta is like word w2 at time tß") can effectively be modeled with diachronic word embeddings, provided that the independent embedding spaces from each time period are appropriately transformed into a common vector space. When applied to a diachronic corpus of news articles, this method is able to identify temporal word analogies such as "Ronald Reagan in 1987 is like Bill Clinton in 1997", or "Walkman in 1987 is like iPod in 2007". en
dc.description.sponsorship Science Foundation Ireland en
dc.language.iso en en
dc.publisher Association for Computational Linguistics en
dc.relation.ispartof Barzilay, R., Kan MY. (eds.) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) en
dc.rights Licensed on a Creative Commons Attribution 4.0 License. en
dc.subject Temporal word analogies en
dc.subject Vector space models en
dc.title Temporal Word Analogies: Identifying Lexical Replacement with Diachronic Word Embeddings en
dc.type Conference Publication en
dc.status Peer reviewed en
dc.identifier.doi 10.18653/v1/P17-2071
dc.neeo.contributor Szymanski|Terrence|aut|
dc.date.updated 2017-08-04T10:27:14Z

This item appears in the following Collection(s)

Show simple item record

This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.

If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.

Search Research Repository

Advanced Search