Essentia: Mining Domain-Specific Paraphrases with Word-Alignment Graphs

Ma, Danni; Chen, Chen; Golshan, Behzad; Tan, Wang-Chiew

doi:10.48550/arxiv.1910.00637

Cited by 2 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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.…”

Section: Related Workmentioning

confidence: 99%

PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge

Wang

Zhang

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We present a new benchmark dataset called PARADE for paraphrase identification that requires specialized domain knowledge. PA-RADE contains paraphrases that overlap very little at the lexical and syntactic level but are semantically equivalent based on computer science domain knowledge, as well as nonparaphrases that overlap greatly at the lexical and syntactic level but are not semantically equivalent based on this domain knowledge. Experiments show that both state-of-the-art neural models and non-expert human annotators have poor performance on PARADE. For example, BERT after fine-tuning achieves an F1 score of 0.709, which is much lower than its performance on other paraphrase identification datasets. PARADE can serve as a resource for researchers interested in testing models that incorporate domain knowledge. We make our data and code freely available. 1

show abstract

Section: Related Workmentioning

confidence: 99%