JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A54UI3UDQ" target="_blank" >RIV/00216208:11320/23:54UI3UDQ - isvavai.cz</a>
Výsledek na webu
<a href="http://arxiv.org/abs/2311.04192" target="_blank" >http://arxiv.org/abs/2311.04192</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.48550/arXiv.2311.04192" target="_blank" >10.48550/arXiv.2311.04192</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models
Popis výsledku v původním jazyce
"Image captioning studies heavily rely on automatic evaluation metrics such as BLEU and METEOR. However, such n-gram-based metrics have been shown to correlate poorly with human evaluation, leading to the proposal of alternative metrics such as SPICE for English; however, no equivalent metrics have been established for other languages. Therefore, in this study, we propose an automatic evaluation metric called JaSPICE, which evaluates Japanese captions based on scene graphs. The proposed method generates a scene graph from dependencies and the predicate-argument structure, and extends the graph using synonyms. We conducted experiments employing 10 image captioning models trained on STAIR Captions and PFN-PIC and constructed the Shichimi dataset, which contains 103,170 human evaluations. The results showed that our metric outperformed the baseline metrics for the correlation coefficient with the human evaluation."
Název v anglickém jazyce
JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models
Popis výsledku anglicky
"Image captioning studies heavily rely on automatic evaluation metrics such as BLEU and METEOR. However, such n-gram-based metrics have been shown to correlate poorly with human evaluation, leading to the proposal of alternative metrics such as SPICE for English; however, no equivalent metrics have been established for other languages. Therefore, in this study, we propose an automatic evaluation metric called JaSPICE, which evaluates Japanese captions based on scene graphs. The proposed method generates a scene graph from dependencies and the predicate-argument structure, and extends the graph using synonyms. We conducted experiments employing 10 image captioning models trained on STAIR Captions and PFN-PIC and constructed the Shichimi dataset, which contains 103,170 human evaluations. The results showed that our metric outperformed the baseline metrics for the correlation coefficient with the human evaluation."
Klasifikace
Druh
O - Ostatní výsledky
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů