AdTEC: A Unified Benchmark for Evaluating Text Quality in Search Engine Advertising

AbstractAs the fluency of ad texts automatically generated by natural language generation technologies continues to improve, there is an increasing demand to assess the quality of these creatives in real-world setting.We propose **AdTEC**, the first public benchmark to evaluate ad texts from multiple perspectives within practical advertising operations.Our contributions are as follows: (i) Defining five tasks for evaluating the quality of ad texts, as well as constructing a Japanese dataset based on the practical operational experiences of advertising agencies, which are typically maintained in-house. (ii) Validating the performance of existing pre-trained language models (PLMs) and human evaluators on this dataset. (iii) Analyzing the characteristics and providing challenges of the benchmark.Our results show that while PLMs have a practical level of performance in several tasks, humans continue to outperform them in certain domains, indicating that there remains significant potential for further improvement in this area.