English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 DetailsSummary
  Structure-(in)dependent interpretation of phrases in humans and LSTMs

Coopmans, C. W., De Hoop, H., Kaushik, K., Hagoort, P., & Martin, A. E. (2021). Structure-(in)dependent interpretation of phrases in humans and LSTMs. In Proceedings of the Society for Computation in Linguistics (SCiL 2021) (pp. 459-463).

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-0008-139C-3 Version Permalink: https://hdl.handle.net/21.11116/0000-0008-139D-2
Genre: Conference Paper

Files

show Files
hide Files
:
Structure-(in)dependent Interpretation of Phrases in Humans and LSTMs.pdf (Publisher version), 459KB
View   Save
File Permalink:
https://hdl.handle.net/21.11116/0000-0008-139E-1
Name:
Structure-(in)dependent Interpretation of Phrases in Humans and LSTMs.pdf
Description:
-
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
2021
Copyright Info:
-
License:
-

Locators

show
hide
Locator:
full text via ScholarWorks@UMass Amherst (Supplementary material)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Coopmans, Cas W.1, 2, 3, 4, Author           
De Hoop, Helen2, Author
Kaushik, Karthikeya3, Author
Hagoort, Peter1, 5, Author           
Martin, Andrea E.3, 5, Author           
Affiliations:
1Neurobiology of Language Department, MPI for Psycholinguistics, Max Planck Society, ou_persistent22              
2Centre for Language Studies, External Organizations, ou_persistent22              
3Language and Computation in Neural Systems, MPI for Psycholinguistics, Max Planck Society, ou_3217300              
4International Max Planck Research School for Language Sciences, MPI for Psycholinguistics, Max Planck Society, Nijmegen, NL, ou_1119545              
5Donders Institute for Brain, Cognition and Behaviour, External Organizations, ou_55236              

Content

show
hide
Free keywords: -
 Abstract: In this study, we compared the performance of a long short-term memory (LSTM) neural network to the behavior of human participants on a language task that requires hierarchically structured knowledge. We show that humans interpret ambiguous noun phrases, such as second blue ball, in line with their hierarchical constituent structure. LSTMs, instead, only do
so after unambiguous training, and they do not systematically generalize to novel items. Overall, the results of our simulations indicate that a model can behave hierarchically without relying on hierarchical constituent structure.

Details

show
hide
Language(s): eng - English
 Dates: 2021
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: The Society for Computation in Linguistics (SCiL 2021)
Place of Event: -
Start-/End Date: 2021-02-14 - 2021-02-19

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of the Society for Computation in Linguistics (SCiL 2021)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: 5 Volume / Issue: 4 Sequence Number: - Start / End Page: 459 - 463 Identifier: -