Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ CORE (RIOXX-UK Aggre...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 6 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Language comprehension as a multi‐label classification problem

Authors: Sering, K.; Milin, P.; Baayen, R.H.;

Language comprehension as a multi‐label classification problem

Abstract

The initial stage of language comprehension is a multi-label\ud classification problem. Listeners or readers, presented with\ud an utterance, need to discriminate between the intended\ud words and the tens of thousands of other words they know.\ud We propose to address this problem by pairing a network\ud trained with the learning rule of Rescorla andWagner (1972)\ud with a second network trained independently with the learning\ud rule of Widrow and Hoff (1960). The first network has\ud to recover from sublexical input features the meanings encoded\ud in the language signal, resulting in a vector of activations\ud over the lexicon. The second network takes this\ud vector as input and further reduces uncertainty about the\ud intended message. Classification performance for a lexicon\ud with 52,000 entries is good. The model also correctly predicts\ud several aspects of human language comprehension. By\ud rejecting the traditional linguistic assumption that language\ud is a (de)compositional system, and by instead espousing a\ud discriminative approach (Ramscar, 2013), a more parsimonious\ud yet highly effective functional characterization of the\ud initial stage of language comprehension is obtained.

Related Organizations
Subjects by Vocabulary

Microsoft Academic Graph classification: Multi-label classification business.industry Computer science SIGNAL (programming language) Characterization (mathematics) computer.software_genre Lexicon Comprehension Discriminative model Learning rule Artificial intelligence business computer Natural language processing Utterance

Keywords

Statistics and Probability, Statistics, Probability and Uncertainty

17 references, page 1 of 2

TA B L E 3

Arnold, D., Tomaschek, F., Lopez, F., Sering, T. and Baayen, R. H. (2017) Words from spontaneous conversational speech can be recognized with human-like accuracy by an error-driven learning algorithm that discriminates between meanings straight from smart acoustic features, bypassing the phoneme as recognition unit. PLOS ONE, 12, e0174623. URL: http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0174623.

Baayen, R. H., Tomaschek, F., Gahl, S. and Ramscar, M. (2017) The Ecclesiastes principle in language change. In The changing English language: Psycholinguistic perspectives (eds. M. Hundt, S. Mollin and S. Pfenninger), in press. Cambridge, UK: Cambridge University Press. [OpenAIRE]

Bruni, E., Tran, N. and Baroni, M. (2014) Multimodal distributional semantics. Journal of Artificial Intelligence Research, 49, 1-47.

Dalal, N. and Triggs, B. (2005) Histograms of oriented gradients for human detection. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), vol. 1, 886-893.

Firth, J. R. (1968) Selected papers of J R Firth, 1952-59. Indiana University Press.

Kalman, R. E. (1960) A new approach to linear filtering and prediction problems. Journal of basic Engineering, 82, 35-45.

Landauer, T. and Dumais, S. (1997) A solution to Plato's problem: The latent semantic analysis theory of acquisition, induction and representation of knowledge. Psychological Review, 104, 211-240.

Linke, M., Broeker, F., Ramscar, M. and Baayen, R. H. (2017) Are baboons learning “orthographic” representations? probably not. PLOS-ONE, 12, e0183876.

Ramscar, M. (2013) Suffixing, prefixing, and the functional order of regularities in meaningful strings. Psihologija, 46, 377-396. [OpenAIRE]

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    8
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 10%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 35
    download downloads 86
  • citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    8
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 10%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    Powered byBIP!BIP!
  • 35
    views
    86
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
8
Top 10%
Average
Average
35
86
bronze