[Corpora-List] Geometrical representation of NL phrases for similarity comparison

Eric Atwell E.S.Atwell at leeds.ac.uk
Fri Oct 19 11:12:35 CEST 2018


SEMEVAL 2017 Task 1 investigated "Semantic Textual Similarity" in English, Spanish, Arabic sentences, see http://alt.qcri.org/semeval2017/task1/ and

Proceedings https://aclanthology.coli.uni-saarland.de/events/semeval-2017#S17-2

Eric Atwell, Professor of AI4L Artificial Intelligence for Language

Best Lecturer 2017 award from COMPSOC Computing Student Society

School of Computing, Uni of LEEDS *** Times Uni of the Year 2017 ***

________________________________ From: corpora-bounces at uib.no <corpora-bounces at uib.no> on behalf of Alexander Osherenko <osherenko at gmx.de> Sent: 19 October 2018 09:41:08 To: Corpora at uib.no Subject: [Corpora-List] Geometrical representation of NL phrases for similarity comparison


I wonder if it is possible to represent NL phrases geometrically, for example, to compare their similarity. For example, the phrase "Hey man, that chick is such a catch!" and more formal "..., this girl is pretty!" should be represented geometrically nearby because they are semantically similar.

I am aware of LSA vectors that represent particular words and similarity could be evaluated as a distance between these word vectors in the LSA space. However, the LSA approach only works for individual words and no phrases and it is IMHO too numerical because it doesn't consider semantics of participating words.

Best, Alexander -- Alexander Osherenko, Dr. rer. nat. Senior HCI architect Founder and R&D Socioware Development<http://www.socioware.de/osherenko_page.html> Profile: ResearchGate<https://www.researchgate.net/profile/Alexander_Osherenko> Implementing Social Smart Environments with a Large Number of Believable Inhabitants in the Context of Globalization<https://www.researchgate.net/publication/327425719_Implementing_Social_Smart_Environments_with_a_Large_Number_of_Believable_Inhabitants_in_the_Context_of_Globalization> at Springer -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 4777 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20181019/260b9021/attachment.txt>

More information about the Corpora mailing list