Since the Scientific Literature Is Multilingual, Our Models Should Be Too

arXiv:2403.18251v1 Announce Type: new
Abstract: English has long been assumed the $\textit{lingua franca}$ of scientific research, and this notion is reflected in the natural language processing (NLP) research involving scientific document representation. In this position piece, we quantitatively show that the literature is largely multilingual and argue that current models and benchmarks should reflect this linguistic diversity. We provide evidence that text-based models fail to create meaningful representations for non-English papers and highlight the negative user-facing impacts of using English-only …

abstract arxiv cs.cl current document english language language processing lingua franca literature multilingual natural natural language natural language processing nlp notion processing representation research scientific scientific research show type