Abstract Lexical Simplification (LS) is the task of substituting complex words within a sentence for simpler alternatives while maintaining the sentence’s original meaning. LS is the lexical component of Text Simplification (TS) systems with the aim of improving accessibility to various target populations such as individuals with low literacy or reading disabilities. Prior surveys have been published several years before the introduction of transformers, transformer-based large language models (LLMs), and prompt learning that have drastically changed the field of NLP. The high performance of these models has sparked renewed interest in LS. To reflect these recent advances, we present a comprehensive survey of papers published since 2017 on LS and its sub-tasks focusing on deep learning. Finally, we describe available benchmark datasets for the future development of LS systems.

Abstract Recent work on text simplification has focused on the use of control tokens to further the state-of-the-art. However, it is not easy to further improve without an in-depth comprehension of the mechanisms underlying control tokens. One unexplored factor is the tokenization strategy, which we also explore. In this paper, we (1) reimplemented AudienCe-CEntric Sentence Simplification, (2) explored the effects and interactions of varying control tokens, (3) tested the influences of different tokenization strategies, (4) demonstrated how separate control tokens affect performance and (5) proposed new methods to predict the value of control tokens. We show variations of performance in the four control tokens separately. We also uncover how the design of control tokens could influence performance and give some suggestions for designing control tokens. We show the newly proposed method with higher performance in both SARI (a common scoring metric in text simplificaiton) and BERTScore (a score derived from the BERT language model) and potential in real applications.

Tannon Kew, Alison Chi, Laura Vásquez-Rodríguez, Sweta Agrawal, Dennis Aumiller, Fernando Alva-Manchego, Matthew Shardlow. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

This project investigates the capabilities of Machine Translation models for generating translations at varying levels of readability, focusing on texts related to COVID-19. Whilst it is possible to automatically translate this information, the resulting text may contain specialised terminology, or may be written in a style that is difficult for lay readers to understand. So far, we have collected a new dataset with manual simplifications for English and Spanish sentences in the TICO-19 dataset, as well as implemented baseline pipelines combining Machine Translation and Text Simplification models.

Practitioner written grey literature, such as blog articles, has value in software engineering research. Such articles provide insight into practice that is often not visible to research. However, a high quantity and varying quality are two major challenges in utilising such material. Quality is defined as an aggregate of a document’s relevance to the consumer and its credibility. Credibility is often assessed through a series of conceptual criteria that are specific to a particular user group. For researchers, previous work has found ‘argumentation’ and ‘evidence’ to be two important criteria.

Specialist high-quality information is typically first available in English, and it is written in a language that may be difficult to understand by most readers. While Machine Translation technologies contribute to mitigate the first issue, the translated content will most likely still contain complex language. In order to investigate and address both problems simultaneously, we introduce Simple TICO-19, a new language resource containing manual simplifications of the English and Spanish portions of the TICO-19 corpus for Machine Translation of COVID-19 literature. We provide an in-depth description of the annotation process, which entailed designing an annotation manual and employing four annotators (two native English speakers and two native Spanish speakers) who simplified over 6,000 sentences from the English and Spanish portions of the TICO-19 corpus. We report several statistics on the new dataset, focusing on analysing the improvements in readability from the original texts to their simplified versions. In addition, we propose baseline methodologies for automatically generating the simplifications, translations and joint translation and simplifications contained in our dataset.

In this work, we uncover a hidden linguistic property of emoji, namely that they are polysemous and can be used to form a semantic network of emoji meanings. Our key contributions to this direction of study are as follows: (1) We have developed a new corpus to help in the task of emoji sense prediction. This corpus contains tweets with single emojis, where each emoji has been labelled with an appropriate sense identifier from WordNet. (2) Experiments, which demonstrate that it is possible to predict the sense of an emoji using our corpus to a reasonable level of accuracy. We are able to report an average path-similarity score of 0.4146 for our best emoji sense prediction algorithm. (3) We further show that emoji sense is a useful feature in the emoji prediction task, where we report an accuracy of 58.8816 and macro-F1 score of 46.6640, beating reasonable baselines in this task. Our work demonstrates that importance of considering the meaning behind emoji, rather than ignoring them, or simply treating them as extra wordforms.

Background: Blogs are a source of grey literature which are widely adopted by software practitioners for disseminating opinion and experience. Analysing such articles can provide useful insights into the state–of–practice for software engineering research. However, there are challenges in identifying higher quality content from the large quantity of articles available. Credibility assessment can help in identifying quality content, though there is a lack of existing corpora. Credibility is typically measured through a series of conceptual criteria, with ’argumentation’ and ’evidence’ being two important criteria.

In this work we propose the task of multi-word lexical simplification, in which a sentence in natural language is made easier to understand by replacing its fragment with a simpler alternative, both of which can consist of many words.In order to explore this new direction, we contribute a corpus (MWLS1), including 1462 sentences in English from various sources with 7059 simplifications provided by human annotators.We also propose an automatic solution (Plainifier) based on a purpose-trained neural language model and evaluate its performance, comparing to human and resource-based baselines.

This work presents a replication study of Exploring Neural Text Simplification Models (Nisioi et al., 2017). We were able to successfully replicate and extend the methods presented in the original paper. Alongside the replication results, we present our improvements dubbed CombiNMT. By using an updated implementation of OpenNMT, and incorporating the Newsela corpus alongside the original Wikipedia dataset (Hwang et al., 2016), as well as refining both datasets to select high quality training examples. Our work present two new systems, CombiNMT995, which is a result of matched sentences with a cosine similarity of 0.995 or less, and CombiNMT98, which, similarly, runs on a cosine similarity of 0.98 or less. By extending the human evaluation presented within the original paper, increasing both the number of annotators and the number of sentences annotated, with the intention of increasing the quality of the results, CombiNMT998 shows significant improvement over any of the Neural Text Simplification (NTS) systems from the original paper in terms of both the number of changes and the percentage of correct changes made.

Multiword expressions (MWEs) represent lexemes that should be treated as single lexical units due to their idiosyncratic nature. Multiple NLP applications have been shown to benefit from MWE identification, however the research on lexical complexity of MWEs is still an under-explored area. In this work, we re-annotate the Complex Word Identification Shared Task 2018 dataset of Yimam et al. (2017), which provides complexity scores for a range of lexemes, with the types of MWEs. We release the MWE-annotated dataset with this paper, and we believe this dataset represents a valuable resource for the text simplification community. In addition, we investigate which types of expressions are most problematic for native and non-native readers. Finally, we show that a lexical complexity assessment system benefits from the information about MWE types.

Clinical letters are infamously impenetrable for the lay patient.This work uses neural text simplification methods to automatically improve the understandability of clinical letters for patients.We take existing neural text simplification software and augment it with a new phrase table that links complex medical terminology to simpler vocabulary by mining SNOMED-CT.In an evaluation task using crowdsourcing, we show that the results of our new system are ranked easier to understand (average rank 1.93) than using the original system (2.34) without our phrase table.We also show improvement against baselines including the original text (2.79) and using the phrase table without the neural text simplification software (2.94).Our methods can easily be transferred outside of the clinical domain by using domain-appropriate resources to provide effective neural text simplification for any domain without the need for costly annotation.

OBJECTIVE: The abundance of text available in social media and health related forums along with the rich expression of public opinion have recently attracted the interest of the public health community to use these sources for pharmacovigilance. Based on the intuition that patients post about Adverse Drug Reactions (ADRs) expressing negative sentiments, we investigate the effect of sentiment analysis features in locating ADR mentions. METHODS: We enrich the feature space of a state-of-the-art ADR identification method with sentiment analysis features. Using a corpus of posts from the DailyStrength forum and tweets annotated for ADR and indication mentions, we evaluate the extent to which sentiment analysis features help in locating ADR mentions and distinguishing them from indication mentions. RESULTS: Evaluation results show that sentiment analysis features marginally improve ADR identification in tweets and health related forum posts. Adding sentiment analysis features achieved a statistically significant F-measure increase from 72.14% to 73.22% in the Twitter part of an existing corpus using its original train/test split. Using stratified 10×10-fold cross-validation, statistically significant F-measure increases were shown in the DailyStrength part of the corpus, from 79.57% to 80.14%, and in the Twitter part of the corpus, from 66.91% to 69.16%. Moreover, sentiment analysis features are shown to reduce the number of ADRs being recognized as indications. CONCLUSION: This study shows that adding sentiment analysis features can marginally improve the performance of even a state-of-the-art ADR identification method. This improvement can be of use to pharmacovigilance practice, due to the rapidly increasing popularity of social media and health forums.