“…Hence, we present PARADE, the first sentential dataset for paraphrase identification based on domain knowledge as shown in Table 1, as a complement to these previous efforts. Domain-Specific Phrasal Paraphrases: Some previous work aims to extract domain-specific phrasal paraphrases (Pavlick et al, 2015;Zhang et al, 2016;Ma et al, 2019), like "head" and "skull" in the Biology domain. In this paper, we focus on sentential paraphrases rather than phrasal paraphrases, which require models that consider context and domain knowledge.…”