GiCCS: A German in-Context Conversational Similarity Benchmark

no code implementations • Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM) 2022 • Shima Asaadi, Zahra Kolagar, Alina Liebel, Alessandra Zarcone

We argue for the need of benchmarks specifically created using conversational data in order to evaluate conversational LMs in the STS task.

Benchmarking Semantic Textual Similarity +1