DynaSent
홈페이지 · 논문 16편
DynaSent is an English-language benchmark task for ternary (positive/negative/neutral) sentiment analysis. DynaSent combines naturally occurring sentences with sentences created using the open-source Dynabench Platform, which facilities human-and-model-in-the-loop dataset creation. DynaSent has a total of 121,634 sentences, each validated by five crowdworkers. Source: [DynaSent: A Dynamic Benchmark for Sentiment Analysis](/paper/dynasent-a-dynamic-benchmark-for-sentiment)