French Biomedical Text Simplification: When Small and Precise Helps

Proceedings of the 28th International Conference on Computational Linguistics, pages 710–716 Barcelona, Spain (Online), December 8-13, 2020 710 French Biomedical Text Simplification: When Small and Precise Helps Rémi Cardon, Natalia Grabar UMR CNRS 8163 – STL, Université de Lille F-59000 Lille, France remi.cardon@univ-lille.fr, natalia.grabar@univ-lille.fr Abstract We present experiments on biomedical text simplification in French. We use two kinds of corpora – parallel sentences extracted from existing health comparable corpora in French and WikiLarge corpus translated from English to French – and a lexicon that associates medical terms with paraphrases. Then, we train neural models on these parallel corpora using different ratios of general and specialized sentences. We evaluate the results with BLEU, SARI and Kandel scores. The results point out that little specialized data helps significantly the simplification. 1 Introduction The goal of text simplification is to make complex texts accessible to a given target audience (children, foreigners, diseased people...) or to make complex texts to be more easily processed by NLP applications. There is little existing work on biomedical text simplification in English (Peng et al., 2012; Shardlow and Nawaz, 2019), and on text simplification for the general language in French (Abdul Rauf et al., 2020; Gala et al., 2020; Sauvan et al., 2020; Brouwers et al., 2014). Research on text simplification is usually performed on open domain English. Currently used methods rely on deep learning approaches and require large parallel monolingual corpora in which one complex sentence is paired with one or more simplified versions (Nisioi et al., 2017; Cooper and Shardlow, 2020). Two English datasets are commonly used: (1) Newsela (Xu et al., 2015), a corpus with news articles that are manually re-written according to four levels of simplification, and (2) WikiLarge (Zhang and Lapata, 2017), issued from a compilation of three previously released simplification corpora all extracted from Wikipedia (Zhu et al., 2010; Woodsend and Lapata, 2011; Kauchak, 2013). The availability of corpora and resources plays indeed a very important role and condition the feasibility of the NLP research. We build and test models for biomedical text simplification in French. We first describe the data used (Section 2) and various configurations of the experiments (Section 3). We then indicate the evaluation principles (Section 4), and present and discuss the results (Section 5). We also provide the WikiLarge FR corpus and a set of native parallel sentences in French, from general and biomedical languages. 2 Linguistic Data Total Train Validation Test Corpus Pairs Tokens Pairs Tokens Pairs Tokens Pairs Tokens WikiLarge FR 297,494 12,753,567 296,402 12,695,192 992 42,676 100 4,302 CLEAR 4,596 226,149 4,196 206,500 300 7,381 100 4,965 Table 1: Size of the two parallel corpora We use two sets of parallel corpora dedicated to the simplification. One set is obtained from the freely available simplification corpus CLEAR in French (Grabar and Cardon, 2018). This is a comparable This work is licensed under a Creative Commons Attribution 4.0 International License. License details: http:// creativecommons.org/licenses/by/4.0/. 711 corpus, which contains three types of texts (medical literature reviews, drug …

Content truncated to 500 words