Automatic Simplification of Scientific Texts: SimpleText Lab at CLEF-2022

Abstract

The Web and social media have become the main source of information for citizens, with the risk that users rely on shallow information in sources prioritizing commercial or political incentives rather than the correctness and informational value. Non-experts tend to avoid scientific literature due to its complex language or their lack of prior background knowledge. Text simplification promises to remove some of these barriers. The CLEF 2022 SimpleText track addresses the challenges of text simplification approaches in the context of promoting scientific information access, by providing appropriate data and benchmarks, and creating a community of NLP and IR researchers working together to resolve one of the greatest challenges of today. The track will use a corpus of scientific literature abstracts and popular science requests. It features three tasks. First, content selection (what is in, or out?) challenges systems to select passages to include in a simplified summary in response to a query. Second, complexity spotting (what is unclear?) given a passage and a query, aims to rank terms/concepts that are required to be explained for understanding this passage (definitions, context, applications). Third, text simplification (rewrite this!) given a query, asks to simplify passages from scientific abstracts while preserving the main content.

Clear, easy, plain, and simple as keywords for text simplification

“…Formal processes of text simplification are varied (Siddharthan, 2014 ; François, 2018 ; Garbacea et al, 2021 ; Ermakova et al, 2022 ). In this regard, Garbacea et al ( 2021 ) emphasize the persistent ambiguity of this phrase, which can refer to different linguistic levels, that is, lexical, syntactic, and semantic, and the way it is conducted, whether manual or automatic, etc.…”

Towards Self-Contained Answers: Entity-Based Answer Rewriting in Conversational Search

“…However, researchers have studied text rewriting in IR for personalization and text simplification. While text simplification has been shown to improve readability and understanding in medical [24] and scientific texts [12], it is usually done by swapping relatively unfamiliar words with more common alternative words [24] or leveraging large-scale language models for complete rewriting of the text [34]. In this setting, a certain degree of information distortion is acceptable, as the text rewritten with such methods might differ from the original due to word substitutions.…”

Overview of the CLEF 2022 SimpleText Lab: Automatic Simplification of Scientific Texts

“…Train dataset. For this task, data is two-fold: Medicine and Computer Science, as these two domains are the most popular on forums like ELI5 [12,29]. As in 2021, for Computer Science, we use scientific abstracts from the Citation Network Dataset: DBLP+Citation, ACM Citation network (12th version) 7 [10].…”

“…Train dataset As for Task 2: What is unclear?, we provided a parallel corpus of simplified sentences from two domains: Medicine and Computer Science (see Section 4.1). As previously, we use scientific abstracts from the DBLP Citation Network Dataset for Computer Science and Google Scholar and PubMed articles on muscle hypertrophy and health Medicine [10,12].…”

“…Text passages issued from abstracts on computer science were simplified by either a master student in Technical Writing and Translation or a pair of experts: (1) a computer scientist and (2) a professional translator, English native speaker but not specialist in computer science [12]. Each passage was discussed and rewritten multiple times until it became clear for non-computer scientists.…”