Lexical Simplification Research Articles

Evaluating Medical Lexical Simplification: Rule-Based vs. BERT.

Lexical simplification (LS) can decrease the communication gap between medical experts and laypeople by replacing medical terms with layperson counterparts. In this paper, we present: 1) a rule-based approach to LS using a consumer health vocabulary, and 2) an unsupervised approach using BERT to generate word candidates. Human evaluation shows that the unsupervised model performed better for simplicity and grammaticality, while the rule-based method was better at meaning preservation.

Thalamic but Not Subthalamic Neuromodulation Simplifies Word Use in Spontaneous Language.

Several investigations have shown language impairments following electrode implantation surgery for Deep Brain Stimulation (DBS) in movement disorders. The impact of the actual stimulation, however, differs between DBS targets with further deterioration in formal language tests induced by thalamic DBS in contrast to subtle improvement observed in subthalamic DBS. Here, we studied speech samples from interviews with participants treated with DBS of the thalamic ventral intermediate nucleus (VIM) for essential tremor (ET), or the subthalamic nucleus (STN) for Parkinson’s disease (PD), and healthy volunteers (each n = 13). We analyzed word frequency and the use of open and closed class words. Active DBS increased word frequency in case of VIM, but not STN stimulation. Further, relative to controls, both DBS groups produced fewer open class words. Whereas VIM DBS further decreased the proportion of open class words, it was increased by STN DBS. Thus, VIM DBS favors the use of relatively common words in spontaneous language, compatible with the idea of lexical simplification under thalamic stimulation. The absence or even partial reversal of these effects in patients receiving STN DBS is of interest with respect to biolinguistic concepts suggesting dichotomous thalamic vs. basal ganglia roles in language processing.

Лексические трансформации в языке революционных газет (на материале «Народной газеты»)

The paper aims to determine lexical innovations in the language of the 1917 newspaper. Scientific originality of the study lies in the fact that the author for the first time identifies lexical transformations introduced into the Russian language in 1917. The conducted research allows concluding that “Narodnaya Gazeta” actively used social-political, emotional-expressive, colloquial vocabulary, borrowings and lexical neologisms. It is noted that lexical simplification serves to make the text understandable and available to readers. Lexical innovations were introduced in order to propagate revolutionary ideology and to motivate workers to read this ideologically oriented newspaper.

Lexical Simplification: a Universal Feature of Translation

The present paper explores simplification as one feature of translation universals from English into Arabic. It aims at investigating how much the translators were aware of lexical simplification as a universal feature in the translated texts and discovering to what extent the language of translation is simple in order to preserve the meaning and information to make the translated texts more reader-friendly .this study hypothesizes that the language of translation is assumed to be lexically simpler than that of non-translated target-language texts and characterized by a low level of information flow by reducing lexical density.
 This study adopts certain lexical simplification strategies like using more frequent words, methods to avoid lexical repetition and lexical omission of unnecessary word.
 The data chosen for analysis in the current study include a test involving 10 English literary texts selected from the famous novel the Pride and Prejudice written by Jane Austen in 1813 and translated by six participants as Junior teachers and M.A. students in the Department of Translation – College of Arts – University of Mosul, some of them were provided deliberately with a list of recommended strategies.

When text simplification is not enough: could a graph-based visualization facilitate consumers' comprehension of dietary supplement information?

ObjectiveDietary supplements are widely used. However, dietary supplements are not always safe. For example, an estimated 23 000 emergency room visits every year in the United States were attributed to adverse events related to dietary supplement use. With the rapid development of the Internet, consumers usually seek health information including dietary supplement information online. To help consumers access quality online dietary supplement information, we have identified trustworthy dietary supplement information sources and built an evidence–based knowledge base of dietary supplement information—the integrated DIetary Supplement Knowledge base (iDISK) that integrates and standardizes dietary supplement related information across these different sources. However, as information in iDISK was collected from scientific sources, the complex medical jargon is a barrier for consumers’ comprehension. The objective of this study is to assess how different approaches to simplify and represent dietary supplement information from iDISK will affect lay consumers’ comprehension.Materials and MethodsUsing a crowdsourcing platform, we recruited participants to read dietary supplement information in 4 different representations from iDISK: (1) original text, (2) syntactic and lexical text simplification (TS), (3) manual TS, and (4) a graph–based visualization. We then assessed how the different simplification and representation strategies affected consumers’ comprehension of dietary supplement information in terms of accuracy and response time to a set of comprehension questions.ResultsWith responses from 690 qualified participants, our experiments confirmed that the manual approach, as expected, had the best performance for both accuracy and response time to the comprehension questions, while the graph–based approach ranked the second outperforming other representations. In some cases, the graph–based representation outperformed the manual approach in terms of response time.ConclusionsA hybrid approach that combines text and graph–based representations might be needed to accommodate consumers’ different information needs and information seeking behavior.

An experimental eye-tracking study of text adaptation for readers with dyslexia: effects of visual support and word frequency.

Easy-to-read guidelines recommend visual support and lexical simplification to facilitate text processing, but few empirical studies confirm a positive effect from these recommendations in individuals with dyslexia. This study examined the influence of the visual support and lexical simplification on sentence processing through eye movements at both the text- and word-level, and the differences between readers with and without dyslexia. Furthermore, we explored the influence of reading experience and vocabulary, as control variables. We tested 20 young adults with dyslexia and 20 chronological age-matched controls. Participants read 60 sentences in total. Half the sentences contained an image and the other half did not, and half contained a low-frequency word and half a high-frequency word. Results showed that visual support and lexical simplification facilitated sentence processing, potentially by jointly facilitating lexical semantic access. We also found that participants with lower print exposure and lower vocabulary benefited more from word-level lexical simplification. We conclude that both adaptations could benefit readers with low print exposure and smaller vocabularies, and therefore, to many dyslexic readers who show these characteristics.

LSBert: Lexical Simplification Based on BERT

Lexical simplification (LS) aims at replacing complex words with simpler alternatives. LS commonly consists of three main steps: complex word identification, substitute generation, and substitute ranking. Existing LS methods focus on the contextual information of the complex word in the last step (substitute ranking). However, they miss out the following two facts: (1) The word complexity of a polysemous word is very closely related to its context; (2) The step of substitute generation regardless of the context will inevitably produce a large number of spurious candidates. Therefore, we propose a novel LS system LSBert based on pretrained language model BERT to address the aforementioned issues, which is capable of making use of the wider context when both identifying the words in need of simplification and generating substitute candidates for the complex words. Specifically, LSBert consists of a network for complex word identification by fine-tuning BERT and a network for substitute generation based on BERT. Experimental results show that LSBert performs well in both complex word identification and substitute generation, achieving state-of-the-art results in three benchmarks. To facilitate reproducibility, the code of the LSBert system is available at https://github.com/qiang2100/BERT-LS.

Chinese Lexical Simplification

Lexical simplification has attracted much attention in many languages, which is the process of replacing complex words in a given sentence with simpler alternatives of equivalent meaning. Although the richness of vocabulary in Chinese makes the text very difficult to read for children and non-native speakers, there is no research work for the Chinese lexical simplification (CLS) task. To circumvent difficulties in acquiring annotations, we manually create the first benchmark dataset for CLS, which can be used for evaluating the lexical simplification systems automatically. To acquire a more thorough comparison, we present five different types of methods as baselines to generate substitute candidates for the complex word that includes synonym-based approach, word embedding-based approach, BERT-based approach, sememe-based approach, and a hybrid approach. Finally, we design the experimental evaluation of these baselines and discuss their advantages and disadvantages. To our best knowledge, this is the first study for CLS task.

Lexical Simplification System to Improve Web Accessibility

People with intellectual, language and learning disabilities face accessibility barriers when reading texts with complex words. Following accessibility guidelines, complex words can be identified, and easy synonyms and definitions can be provided for them as reading aids. To offer support to these reading aids, a lexical simplification system for Spanish has been developed and is presented in this article. The system covers the complex word identification (CWI) task and offers replacement candidates with the substitute generation and selection (SG/SS) task. These tasks have followed machine learning techniques and contextual embeddings using Easy Reading and Plain Language resources, such as dictionaries and corpora. Additionally, due to the polysemy present in the language, the system provides definitions for complex words, which are disambiguated by a rule-based method supported by a state-of-the-art embedding resource. This system is integrated into a web system that provides an easy way to improve the readability and comprehension of Spanish texts. The results obtained are satisfactory; in the CWI task, better results were obtained than with other systems that used the same dataset. The SG/SS task results are comparable to similar works in the English language and provide a solid starting point to improve this task for the Spanish language. Finally, the results of the disambiguation process evaluation were good when evaluated by a linguistic expert. These findings represent an additional advancement in the lexical simplification of texts in Spanish and in a generic domain using easy-to-read resources, among others, to provide systematic support to compliance with accessibility guidelines.

La riformulazione in inglese del discorso legale italiano come processo di ‘ELFentextualization’

This paper introduces a new model defined ELFentextualization , devised for the English reformulation of the Italian legal discourse in the field of Migration. It is meant as a pedagogical and practical tool that can help intercultural linguistic mediators increase their competence at the time of analysing and reproducing source texts for an audience of non-native English speakers. In particular, our model is adopted here for the retextualization into English as a ‘lingua franca’ (ELF) of a number of extracts from the ‘Bossi-Fini’ law and ‘Testo unico sull’immigrazione’, which indicate the actions that migrants have to follow to request residence document. After illustrating the theoretical grounds of the ELFentextualization process, this paper will examine the selected corpus of English retextualizations of Italian legal discourse. The comparison between the original and ‘ELFentextualized’ versions will exemplify that the latter are elaborated after an initial phase of ‘text analysis’, which is meant to infer the gist of the message. The essential pieces of information are then reconstructed by resorting to lexical and syntactic simplification, as well as to the macrorules for text summarization. Finally, this paper enquires into the initial phases of a reception study of the examined reformulations, which will help discuss the lingua-franca connotation of the English uses in the texts under examination.

Obecność polskich filmów w Niemczech w drugiej połowie lat 30. XX w. Odtworzenie zasad tłumaczenia napisowego

In the 1930s, when national animosities hampered the free circulation of films, only a few Polish titles were released on German screens. One of them is a Polish production from 1936 with star-studded cast titled His Great Love . Preserved in the Polish archive, a copy with German subtitles served as research material and provided the basis for the analyses presented in this paper. The texts of the German subtitles on the tape were precisely noted, after which the number of characters in each of them was counted. They were transcribed with the original division into individual inscriptions and verses. The initial and final codes of each subtitle were also written down. Owing to this, the display time of each subtitle could be estimated. The data on the number of characters in each verse and the time of its display made it possible to calculate the assumed reading rate. The transcription of the characters’ original statements was obtained from the Polish copy. In this way, a tabular list of texts was created. With such research material, it was possible to (1) determine the technical aspects of subtitling, (2) conduct a quantitative comparative analysis of the initial and target texts, and (3) reconstruct the translation strategies and techniques applied. The research showed that the assumed reading rate at that time was about 10 characters per second, which was extremely convenient for the viewers. As a result of the comparative analysis of the output and target texts, it was found that 37.5-38% of dialogues were omitted, but without much harm to the viewer. The result of the abbreviations found in the target text from the 1930s fits into the 30-40% omission range for contemporary subtitles. The identification and interpretation of the translation techniques used demonstrated that the translator of the film studied resorted to the same techniques that are used by contemporary subtitling translators to obtain a compact target text: partial reduction, condensation, paraphrase, lexical or syntactic simplification, and elimination. What is interesting, they resemble contemporary subtitles more than intertitles used in 1930, i.e. only several years earlier than the subtitles for His Great Love .

Language Resources for Japanese Lexical Simplification

Language Resources for Japanese Lexical Simplification

The inhibitory effect of word neighborhood size when reading with central field loss is modulated by word predictability and reading proficiency

For normally sighted readers, word neighborhood size (i.e., the total number of words that can be formed from a single word by changing only one letter) has a facilitator effect on word recognition. When reading with central field loss (CFL) however, individual letters may not be correctly identified, leading to possible misidentifications and a reverse neighborhood size effect. Here we investigate this inhibitory effect of word neighborhood size on reading performance and whether it is modulated by word predictability and reading proficiency. Nineteen patients with binocular CFL from 32 to 89 years old (mean ± SD = 75 ± 15) read short sentences presented with the self-paced reading paradigm. Accuracy and reading time were measured for each target word read, along with its predictability, i.e., its probability of occurrence following the two preceding words in the sentence using a trigram analysis. Linear mixed effects models were then fit to estimate the individual contributions of word neighborhood size, predictability, frequency and length on accuracy and reading time, while taking patients’ reading proficiency into account. For the less proficient readers, who have given up daily reading as a consequence of their visual impairment, we found that the effect of neighborhood size was reversed compared to normally sighted readers and of higher amplitude than the effect of frequency. Furthermore, this inhibitory effect is of greater amplitude (up to 50% decrease in reading speed) when a word is not easily predictable because its chances to occur after the two preceding words in a specific sentence are rather low. Severely impaired patients with CFL often quit reading on a daily basis because this task becomes simply too exhausting. Based on our results, we envision lexical text simplification as a new alternative to promote effective rehabilitation in these patients. By increasing reading accessibility for those who struggle the most, text simplification might be used as an efficient rehabilitation tool and daily reading assistive technology, fostering overall reading ability and fluency through increased practice.

Barriers in Reading Comprehension of University Students: Analysis of the Complicated Words Annotated in the VYTEDU-CW Corpus

Students often require a greater understanding of the lexicon that teachers use when dictating an assignment in class or in written texts as supporting material. Identifying and labelling difficult words has allowed us to examine the problem. A sample of students from the University of Guayaquil (Ecuador) was taken to experiment in a corpus of video transcripts that correspond to the different careers. After performing the analysis of the tagged words, the conclusions reached by other research papers in lexical simplification are confirmed and corroborates the recommendations of the Easy Reading guide prepared by Inclusion Europe in 2009. The investigation determined that the words labeled as difficult were specialized words, common lexical words, slang, English words, acronyms, among others. It was difficult for students to understand its meaning; in some cases, they either ignored its definition or just had the wrong idea of the lexicon. This work aims to be a contribution to future research in the area of lexical simplification applied to the development of solutions for detecting difficult words in the university academic field. Also, the type of complex expressions identified in the VYTEDU-CW corpus were characterized by the software, which enriches this resource while opening the possibility to organize a workshop where to promote research in the detection of difficult words to the Spanish. The support to validate these solutions is available to the scientific community.

Lexical Simplification by Unsupervised Machine Translation

In recent years, simple Japanese has been attracting attention as information transmission for foreigners. Automatic text simplification aims to reduce the complexity of vocabulary and expressions in a sentence while retaining its original meaning. This paper aims at compressing vocabulary, focusing on lexical simplification. Since the construction or expansion of a simplification corpus is very costly, we construct a simplification model by unsupervised learning that does not require a parallel corpus for simplification. We construct a simplification model that does not require a parallel corpus using Unsupervised Statistical Machine Translation. Based on a predetermined vocabulary, a pseudo-corpus for simplification is constructed from a web corpus and we learn the simplification model by the pseudo-corpus. We only need a vocabulary and a plain text corpus to train the simplification model. Moreover, we propose to clean the phrase table by WordNet, which improves the performance in BLEU and SARI metrics. By suppressing distant paraphrasing with WordNet, it became easier to select the correct paraphrase candidate.

Lexical Simplification with Pretrained Encoders

Lexical simplification (LS) aims to replace complex words in a given sentence with their simpler alternatives of equivalent meaning. Recently unsupervised lexical simplification approaches only rely on the complex word itself regardless of the given sentence to generate candidate substitutions, which will inevitably produce a large number of spurious candidates. We present a simple LS approach that makes use of the Bidirectional Encoder Representations from Transformers (BERT) which can consider both the given sentence and the complex word during generating candidate substitutions for the complex word. Specifically, we mask the complex word of the original sentence for feeding into the BERT to predict the masked token. The predicted results will be used as candidate substitutions. Despite being entirely unsupervised, experimental results show that our approach obtains obvious improvement compared with these baselines leveraging linguistic databases and parallel corpus, outperforming the state-of-the-art by more than 12 Accuracy points on three well-known benchmarks.

Design, development and validation of a system for automatic help to medical text understanding

ObjectiveThe paper presents a web-based application, SIMPLE, that facilitates medical text comprehension by identifying the health-related terms of a medical text and providing the corresponding consumer terms and explanations. BackgroundThe comprehension of a medical text is often a difficult task for laypeople because it requires semantic abilities that can differ from a person to another, depending on his/her health-literacy level. Some systems have been developed for facilitating the comprehension of medical texts through text simplification, either syntactical or lexical. The ones dealing with lexical simplification usually replace the original text and do not provide additional information. We have developed a system that provides the consumer terms alongside the original medical terms and also adds consumer explanations. Moreover, differently from other solutions, our system works with multiple languages. MethodsWe have developed the SIMPLE application that is able to automatically: 1) identify medical terms in a medical text by using medical vocabularies; 2) translate the medical terms into consumer terms through medical-consumer thesauri; 3) provide term explanations by using health-consumer dictionaries. SIMPLE can be used as a standalone web application or can it be embedded into common health platforms for real time identification and explanation of medical terms. At present, it works with English and Italian texts but it can be easily extended to other languages. We have run subjective tests with both medical experts and non-experts as well as objective tests to verify the effectiveness of SIMPLE and its simplicity of use. ResultsNon-experts found SIMPLE easy to use and responsive. The big majority of respondents confirmed they were helped by SIMPLE in understanding medical texts and declared their willingness to continue using SIMPLE and to recommend it to other people. The subjective tests, conducted with medical experts on a set of Italian radiology reports, showed an agreement between SIMPLE and the experts, on the highlighted medical terms, that ranges between 74.05 % and 81.16 % as well as an agreement of around 60 % on the consumer term translation. The objective tests showed that the consumer terms, provided by SIMPLE, are, on average, eighteen times more familiar than the relative medical terms so proving, once more, the effectiveness of SIMPLE in simplifying the medical terms. ConclusionsThe performed tests demonstrate the effectiveness of SIMPLE, its simplicity of use and the willingness of people in continuing with its use. SIMPLE provides, with a good agreement level, the same information that medical experts would provide. Finally, the consumer terms are ‘objectively’ more familiar than the related technical terms and as a consequence, much easier to understand.

Lexical simplification approach using easy-to-read resources

This work aims to facilitate the understanding and readability of Spanish texts in a generic domain through the design of a lexical simplification system that provides support to the task of Complex Word Identification (CWI) and selection of a simpler substitute. Considering the limited resources available in Spanish, we explore different features that allow us to discern between a complex word and a simpler one. Some of these features are obtained from easy-to-read resources. The evaluation shows good results by obtaining an F1-Score of 0.7497 on the CWI Task with the BEA Workshop 2018 competition’s dataset.

Simplified or not Simplified? The Different Guises of Mediated English at the European Parliament

In this article we describe a framework for the corpus-based comparative investigation of interpreting and translation, illustrating it through a study of simplification across different modes of language production and across different language pairs. We rely on EPTIC, a corpus featuring plenary speeches at the European Parliament in their interpreted and translated versions, aligned to each other and to their source texts in English<=>Italian and English<=>French. Aiming to shed light on lexical simplification in different mediation modes, we compare interpretations and translations to each other and to comparable original speeches and their edited written versions. Specifically, we compare lexical features (lexical density, type-token ratio, core vocabulary and list head coverage) in interpreting and translation into English from French and Italian, both in a monolingual comparable perspective and an intermodal perspective. Our results do not unconditionally support the simplification hypothesis: lexical simplification is observed in mediated English, but is found to be greater when the source language is French, and in interpretations rather than translations. We conclude that this feature is contingent on both the mediation mode and the source languages involved, and that the influence of the latter seems to be stronger than that of the former.

Linguistic Prehistory and Identity in Nigeria’s Bini-Ife Pre-eminence Contestation

On the basis of genetic classification, Edoid (of the Bini people of Nigeria) is conceivedas an offshoot of Benue-Congo earlier than Yoruboid (of the Ife people of Nigeria).However, the reverse is the case when viewed from the sociolinguistic platforms ofpopulation, prestige and power. Thus, in 2004, the Edoid patriarch of Bini launcheda biography, wherein he narrated the Bini origin of the Ife monarchy. This sparked abarrage of unguarded responses from both sides of the controversy, largely centredon different interpretations to oral tradition. By exploring language as custodian ofprehistory, this paper makes a linguistic contribution to the continuing debate aboutwhich predates the other between Ife (Yoruboid) and Bini (Edoid) of southwesternNigeria. It pieces together evidence of cognate lexical simplification, patterns ofcognate counting systems, sound inventory, and decadence of vowel harmony, whichsupport the chronological pre-eminence of Edoid over Yoruboid; thus, calling forarchaeological, anthropological and geographical inspection.