LexDivPara: A Measure of Paraphrase Quality with Integrated Sentential Lexical Complexity

We present a novel method that automatically measures quality of sentential paraphrasing. Our method balances two conflicting criteria: semantic similarity and lexical diversity. Using a diverse annotated corpus, we built learning to rank models on edit distance, BLEU, ROUGE, and cosine similarity features. Extrinsic evaluation on STS Benchmark and ParaBank Evaluation datasets resulted in a model ensemble with moderate to high quality. We applied our method on both small benchmarking and large-scale datasets as resources for the community.