Barriers and enabling factors for error analysis in NLG research

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475709" target="_blank" >RIV/00216208:11320/23:10475709 - isvavai.cz</a>
Result on the web
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=KKqginXhkU" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=KKqginXhkU</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.3384/nejlt.2000-1533.2023.4529" target="_blank" >10.3384/nejlt.2000-1533.2023.4529</a>

Result language
angličtina
Original language name
Barriers and enabling factors for error analysis in NLG research
Original language description
Earlier research has shown that few studies in Natural Language Generation (NLG) evaluate their system outputs using an error analysis, despite known limitations of automatic evaluation metrics and human ratings. This position paper takes the stance that error analyses should be encouraged, and discusses several ways to do so. This paper is not just based on our shared experience as authors, but we also distributed a survey as a means of public consultation. We provide an overview of existing barriers to carry out error analyses, and proposes changes to improve error reporting in the NLG literature.
Czech name
—
Czech description
—

Type
J<sub>ost</sub> - Miscellaneous article in a specialist periodical
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)