This study sets out to investigate the feasibility of using ChatGPT to translate citizen-oriented administrative texts into German Easy Language, a simplified, rule-based language variety that is adapted to the needs of people with reading impairments. We use ChatGPT to translate selected texts from websites of German public authorities using two strategies, i.e. linguistic and holistic. We analyse the quality of the generated texts based on different criteria, such as correctness, readability, and syntactic complexity. The results indicated that the generated texts are easier than the standard texts, but that they still do not fully meet the established Easy Language standards. Additionally, the content is not always rendered correctly.
We present results from the development and evaluation of context-aware Lexical simplification (LS) systems for the Swedish language. Three versions of LS models, LäsBERT, LäsBERT-baseline, and LäsGPT, were created and evaluated on a newly constructed Swedish LS evaluation dataset. The LS systems demonstrated promising potential in aiding audiences with reading difficulties by providing context-aware word replacements. While there were areas for improvement, particularly in complex word identification, the systems showed agreement with human annotators on word replacements.
Natural language understanding is fundamental to knowledge acquisition in today’s information society. However, natural language is often ambiguous with frequent occurrences of complex terms, acronyms, and abbreviations that require substitution and disambiguation, for example, by “translation” from complex to simpler text for better understanding. These tasks are usually difficult for people with limited reading skills, second language learners, and non-native speakers. Hence, the development of text simplification systems that are capable of simplifying complex text is of paramount importance. Thus, we conducted a user study to identify which components are essential in a text simplification system. Based on our findings, we proposed an improved text simplification framework, covering a broader range of aspects related to lexical simplification — from complexity identification to lexical substitution and disambiguation — while supplementing the simplified outputs with additional information for better understandability. Based on the improved framework, we developed TextSimplifier, a modularised, context-sensitive, end-to-end simplification framework, and engineered its web implementation. This system targets lexical simplification that identifies complex terms and acronyms followed by their simplification through substitution and disambiguation for better understanding of complex language.
This paper explores the readability of translated and interpreted texts compared to the original source texts and target language texts in the same domain. It was shown in the literature that translated and interpreted texts could exhibit lexical and syntactic properties that make them simpler, and hence, easier to process than their sources or comparable non-translations. In translation, this effect is attributed to the tendency to simplify and disambiguate the message. In interpreting, it can be enhanced by the temporal and cognitive constraints. We use readability annotations from the Newsela corpus to formulate a number of classification and regression tasks and fine-tune a multilingual pre-trained model on these tasks, obtaining models that can differentiate between complex and simple sentences. Then, the models are applied to predict the readability of sources, targets, and comparable target language originals in a zero-shot manner. Our test data – parallel and comparable – come from English-German bidirectional interpreting and translation subsets from the Europarl corpus. The results confirm the difference in readability between translated/interpreted targets against sentences in standard originally-authored source and target languages. Besides, we find consistent differences between the translation directions in the English-German language pair.
Lexical simplification traditionally focuses on the replacement of tokens with simpler alternatives. However, in some cases the goal of this task (simplifying the form while preserving the meaning) may be better served by removing a word rather than replacing it. In fact, we show that existing datasets rely heavily on the deletion operation. We propose supervised and unsupervised solutions for lexical deletion based on classification, end-to-end simplification systems and custom language models. We contribute a new silver-standard corpus of lexical deletions (called SimpleDelete), which we mine from simple English Wikipedia edit histories and use to evaluate approaches to detecting superfluous words. The results show that even unsupervised approaches (TerseBERT) can achieve good performance in this new task. Deletion is one part of the wider lexical simplification puzzle, which we show can be isolated and investigated.
We investigate how text genre influences the performance of models for controlled text simplification. Regarding datasets from Wikipedia and PubMed as two different genres, we compare the performance of genre-specific models trained by transfer learning and prompt-only GPT-like large language models. Our experiments showed that: (1) the performance loss of genre-specific models on general tasks can be limited to 2%, (2) transfer learning can improve performance on genre-specific datasets up to 10% in SARI score from the base model without transfer learning, (3) simplifications generated by the smaller but more customized models show similar performance in simplicity and a better meaning reservation capability to the larger generic models in both automatic and human evaluations.
This paper presents the ongoing work conducted within the ClearText project, specifically focusing on the resource creation for the simplification of Spanish for people with cognitive disabilities. These resources include the CLEARSIM corpus and the Simple.Text tool. On the one hand, a description of the corpus compilation process with the help of APSA is detailed along with information regarding whether these texts are bronze, silver or gold standard simplification versions from the original text. The goal to reach is 18,000 texts in total by the end of the project. On the other hand, we aim to explore Large Language Models (LLMs) in a sequence-to-sequence setup for text simplification at the document level. Therefore, the tool’s objectives, technical aspects, and the preliminary results derived from early experimentation are also presented. The initial results are subject to improvement, given that experimentation is in a very preliminary stage. Despite showcasing flaws inherent to generative models (e.g. hallucinations, repetitive text), we examine the resolutions (or lack thereof) of complex linguistic phenomena that can be learned from the corpus. These issues will be addressed throughout the remainder of this project. The expected positive results from this project that will impact society are three-fold in nature: scientific-technical, social, and economic.
In this paper, we report on some experiments aimed at exploring the relation between document-level and sentence-level readability assessment for French. These were run on an open-source tailored corpus, which was automatically created by aggregating various sources from children’s literature. On top of providing the research community with a freely available corpus, we report on sentence readability scores obtained when applying both classical approaches (aka readability formulas) and state-of-the-art deep learning techniques (e.g. fine-tuning of large language models). Results show a relatively strong correlation between document-level and sentence-level readability, suggesting ways to reduce the cost of building annotated sentence-level readability datasets.
We present a coherence-aware evaluation of document-level Text Simplification (TS), an approach that has not been considered in TS so far. We improve current TS sentence-based models to support a multi-sentence setting and the implementation of a state-of-the-art neural coherence model for simplification quality assessment. We enhanced English sentence simplification neural models for document-level simplification using 136,113 paragraph-level samples from both the general and medical domains to generate multiple sentences. Additionally, we use document-level simplification, readability and coherence metrics for evaluation. Our contributions include the introduction of coherence assessment into simplification evaluation with the automatic evaluation of 34,052 simplifications, a fine-tuned state-of-the-art model for document-level simplification, a coherence-based analysis of our results and a human evaluation of 300 samples that demonstrates the challenges encountered when moving towards document-level simplification.
Generative Large Language Models (LLMs), such as GPT-3, have become increasingly effective and versatile in natural language processing (NLP) tasks. One such task is Lexical Simplification, where state-of-the-art methods involve complex, multi-step processes which can use both deep learning and non-deep learning processes. LLaMA, an LLM with full research access, holds unique potential for the adaption of the entire LS pipeline. This paper details the process of fine-tuning LLaMA to create LSLlama, which performs comparably to previous LS baseline models LSBert and UniHD.
Being able to read and understand written text is critical in a digital era. However, studies shows that a large fraction of the population experiences comprehension issues. In this context, further initiatives in accessibility are required to improve the audience text comprehension. However, writers are hardly assisted nor encouraged to produce easy-to-understand content. Moreover, Automatic Text Simplification (ATS) model development suffers from the lack of metric to accurately estimate comprehension difficulty. We present LC-SCORE, a simple approach for training text comprehension metric for any text without reference i.e. predicting how easy to understand a given text is on a [0, 100] scale. Our objective with this scale is to quantitatively capture the extend to which a text suits to the Langage Clair (LC, Clear Language) guidelines, a French initiative closely related to English Plain Language. We explore two approaches: (i) using linguistically motivated indicators used to train statistical models, and (ii) neural learning directly from text leveraging pre-trained language models. We introduce a simple proxy task for comprehension difficulty training as a classification task. To evaluate our models, we run two distinct human annotation experiments, and find that both approaches (indicator based and neural) outperforms commonly used readability and comprehension metrics such as FKGL.
This paper explores the literature of automatic text simplification (ATS) centered on the notion of operations. Operations are the processed of applying certain modifications to a given text in order to transform it. In ATS, the intent of the transformation is to simplify the text. This paper overviews and structures the domain by showing how operations are defined and how they are exploited. We extensively discuss the most recent works on this notion and perform preliminary experiments to automatize operations recognition with large language models (LLMs). Through our overview of the literature and the preliminary experiment with LLMs, this paper provides insights on the topic that can help lead to new directions in ATS research.
In this paper, we present an automated tool with human supervision to write in plain language or to adapt difficult texts into plain language. It can be used on a web version and as a plugin for Word/Outlook plugins. At the publication date, it is only available in the French language. This tool has been developed for 3 years and has been used by 400 users from private companies and from public administrations. Text simplification is automatically performed with the manual approval of the user, at the lexical, syntactic, and discursive levels. Screencast of the demo can be found at the following link: https://www.youtube.com/watch?v=wXVtjfKO9FI.
Readability formulae targeting children have been developed, but their appropriateness can still be improved, for example by taking into account suffixation. Literacy research has identified the suffixation phenomenon makes children’s reading difficult, so we analyze the effectiveness of suffixation within the context of readability. Our analysis finds that suffixation is potentially effective for readability assessment. Moreover, we find that existing readability formulae fail to discern lower grade levels for texts from different existing corpora.