Skip to main navigation Skip to search Skip to main content

Relating semantic similarity and semantic association to how humans label other people

  • Carnegie Mellon University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

Computational linguists have long relied on a distinction between semantic similarity and semantic association to explain and evaluate what is being learned by NLP models. In the present work, we take these same concepts and explore how they apply to an entirely different question - how individuals label other people. Leveraging survey data made public by NLP researchers, we develop our own survey to connect semantic similarity and semantic association to the process by which humans label other people. The result is a set of insights applicable to how we think of semantic similarity as NLP researchers and a new way of leveraging NLP models of semantic similarity and association as researchers of social science.

Original languageEnglish
Title of host publicationNLP + CSS 2016 - EMNLP 2016 Workshop on Natural Language Processing and Computational Social Science, Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages1-10
Number of pages10
ISBN (Electronic)9781945626265
StatePublished - 2016
EventEMNLP 2016 1st Workshop on Natural Language Processing and Computational Social Science, NLP + CSS 2016 - Austin, United States
Duration: Nov 5 2016Nov 5 2016

Publication series

NameNLP + CSS 2016 - EMNLP 2016 Workshop on Natural Language Processing and Computational Social Science, Proceedings of the Workshop

Conference

ConferenceEMNLP 2016 1st Workshop on Natural Language Processing and Computational Social Science, NLP + CSS 2016
Country/TerritoryUnited States
CityAustin
Period11/5/1611/5/16

Fingerprint

Dive into the research topics of 'Relating semantic similarity and semantic association to how humans label other people'. Together they form a unique fingerprint.

Cite this