BrainBench: A Brain-Image Test Suite for Distributional Semantic Models

Haoyan Xu, Brian Murphy, Alona Fyshe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)
168 Downloads (Pure)

Abstract

The brain is the locus of our language ability, and so brain images can be used to ground linguistic theories. Here we introduce Brain-Bench, a lightweight system for testing distributional models of word semantics. We compare the performance of several models, and show that the performance on brain-image tasks differs from the performance on behavioral tasks. We release our benchmark test as part of a web service.
Original languageEnglish
Title of host publication2016 Conference on Empirical Methods on Natural Language: Proceedings
Pages2017-2021
Number of pages5
Publication statusPublished - 05 Nov 2016
EventConference on Empirical Methods in Natural Language Processing - Texas, Austin, United States
Duration: 02 Nov 201606 Nov 2016
http://www.emnlp2016.net/

Conference

ConferenceConference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2016
CountryUnited States
CityAustin
Period02/11/201606/11/2016
Internet address

Fingerprint Dive into the research topics of 'BrainBench: A Brain-Image Test Suite for Distributional Semantic Models'. Together they form a unique fingerprint.

  • Cite this

    Xu, H., Murphy, B., & Fyshe, A. (2016). BrainBench: A Brain-Image Test Suite for Distributional Semantic Models. In 2016 Conference on Empirical Methods on Natural Language: Proceedings (pp. 2017-2021)