Enregistré dans:
Détails bibliographiques
Auteurs principaux: Mita, Masato, Murakami, Soichiro, Kato, Akihiko, Zhang, Peinan
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2309.12030
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913393043046400
author Mita, Masato
Murakami, Soichiro
Kato, Akihiko
Zhang, Peinan
author_facet Mita, Masato
Murakami, Soichiro
Kato, Akihiko
Zhang, Peinan
contents In response to the limitations of manual ad creation, significant research has been conducted in the field of automatic ad text generation (ATG). However, the lack of comprehensive benchmarks and well-defined problem sets has made comparing different methods challenging. To tackle these challenges, we standardize the task of ATG and propose a first benchmark dataset, CAMERA, carefully designed and enabling the utilization of multi-modal information and facilitating industry-wise evaluations. Our extensive experiments with a variety of nine baselines, from classical methods to state-of-the-art models including large language models (LLMs), show the current state and the remaining challenges. We also explore how existing metrics in ATG and an LLM-based evaluator align with human evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2309_12030
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Striking Gold in Advertising: Standardization and Exploration of Ad Text Generation
Mita, Masato
Murakami, Soichiro
Kato, Akihiko
Zhang, Peinan
Computation and Language
In response to the limitations of manual ad creation, significant research has been conducted in the field of automatic ad text generation (ATG). However, the lack of comprehensive benchmarks and well-defined problem sets has made comparing different methods challenging. To tackle these challenges, we standardize the task of ATG and propose a first benchmark dataset, CAMERA, carefully designed and enabling the utilization of multi-modal information and facilitating industry-wise evaluations. Our extensive experiments with a variety of nine baselines, from classical methods to state-of-the-art models including large language models (LLMs), show the current state and the remaining challenges. We also explore how existing metrics in ATG and an LLM-based evaluator align with human evaluations.
title Striking Gold in Advertising: Standardization and Exploration of Ad Text Generation
topic Computation and Language
url https://arxiv.org/abs/2309.12030