Cargando…
Modelling Speaker Attribution in Narrative Texts With Biased and Bias-Adjustable Neural Networks
Literary narratives regularly contain passages that different readers attribute to different speakers: a character, the narrator, or the author. Since literary narratives are highly ambiguous constructs, it is often impossible to decide between diverging attributions of a specific passage by hermene...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8851310/ https://www.ncbi.nlm.nih.gov/pubmed/35187471 http://dx.doi.org/10.3389/frai.2021.725321 |
_version_ | 1784652795810414592 |
---|---|
author | Dönicke, Tillmann Varachkina, Hanna Weimer, Anna Mareike Gödeke, Luisa Barth, Florian Gittel, Benjamin Holler, Anke Sporleder, Caroline |
author_facet | Dönicke, Tillmann Varachkina, Hanna Weimer, Anna Mareike Gödeke, Luisa Barth, Florian Gittel, Benjamin Holler, Anke Sporleder, Caroline |
author_sort | Dönicke, Tillmann |
collection | PubMed |
description | Literary narratives regularly contain passages that different readers attribute to different speakers: a character, the narrator, or the author. Since literary narratives are highly ambiguous constructs, it is often impossible to decide between diverging attributions of a specific passage by hermeneutic means. Instead, we hypothesise that attribution decisions are often influenced by annotator bias, in particular an annotator's literary preferences and beliefs. We present first results on the correlation between the literary attitudes of an annotator and their attribution choices. In a second set of experiments, we present a neural classifier that is capable of imitating individual annotators as well as a common-sense annotator, and reaches accuracies of up to 88% (which improves the majority baseline by 23%). |
format | Online Article Text |
id | pubmed-8851310 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-88513102022-02-18 Modelling Speaker Attribution in Narrative Texts With Biased and Bias-Adjustable Neural Networks Dönicke, Tillmann Varachkina, Hanna Weimer, Anna Mareike Gödeke, Luisa Barth, Florian Gittel, Benjamin Holler, Anke Sporleder, Caroline Front Artif Intell Artificial Intelligence Literary narratives regularly contain passages that different readers attribute to different speakers: a character, the narrator, or the author. Since literary narratives are highly ambiguous constructs, it is often impossible to decide between diverging attributions of a specific passage by hermeneutic means. Instead, we hypothesise that attribution decisions are often influenced by annotator bias, in particular an annotator's literary preferences and beliefs. We present first results on the correlation between the literary attitudes of an annotator and their attribution choices. In a second set of experiments, we present a neural classifier that is capable of imitating individual annotators as well as a common-sense annotator, and reaches accuracies of up to 88% (which improves the majority baseline by 23%). Frontiers Media S.A. 2022-02-03 /pmc/articles/PMC8851310/ /pubmed/35187471 http://dx.doi.org/10.3389/frai.2021.725321 Text en Copyright © 2022 Dönicke, Varachkina, Weimer, Gödeke, Barth, Gittel, Holler and Sporleder. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Artificial Intelligence Dönicke, Tillmann Varachkina, Hanna Weimer, Anna Mareike Gödeke, Luisa Barth, Florian Gittel, Benjamin Holler, Anke Sporleder, Caroline Modelling Speaker Attribution in Narrative Texts With Biased and Bias-Adjustable Neural Networks |
title | Modelling Speaker Attribution in Narrative Texts With Biased and Bias-Adjustable Neural Networks |
title_full | Modelling Speaker Attribution in Narrative Texts With Biased and Bias-Adjustable Neural Networks |
title_fullStr | Modelling Speaker Attribution in Narrative Texts With Biased and Bias-Adjustable Neural Networks |
title_full_unstemmed | Modelling Speaker Attribution in Narrative Texts With Biased and Bias-Adjustable Neural Networks |
title_short | Modelling Speaker Attribution in Narrative Texts With Biased and Bias-Adjustable Neural Networks |
title_sort | modelling speaker attribution in narrative texts with biased and bias-adjustable neural networks |
topic | Artificial Intelligence |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8851310/ https://www.ncbi.nlm.nih.gov/pubmed/35187471 http://dx.doi.org/10.3389/frai.2021.725321 |
work_keys_str_mv | AT donicketillmann modellingspeakerattributioninnarrativetextswithbiasedandbiasadjustableneuralnetworks AT varachkinahanna modellingspeakerattributioninnarrativetextswithbiasedandbiasadjustableneuralnetworks AT weimerannamareike modellingspeakerattributioninnarrativetextswithbiasedandbiasadjustableneuralnetworks AT godekeluisa modellingspeakerattributioninnarrativetextswithbiasedandbiasadjustableneuralnetworks AT barthflorian modellingspeakerattributioninnarrativetextswithbiasedandbiasadjustableneuralnetworks AT gittelbenjamin modellingspeakerattributioninnarrativetextswithbiasedandbiasadjustableneuralnetworks AT holleranke modellingspeakerattributioninnarrativetextswithbiasedandbiasadjustableneuralnetworks AT sporledercaroline modellingspeakerattributioninnarrativetextswithbiasedandbiasadjustableneuralnetworks |