Hasil untuk "English literature"

Wei Li, Adrian de Wynter

It is known that large language models (LLMs) underperform in English dialects, and that improving them is difficult due to data scarcity. In this work we investigate how quality and availability impact the feasibility of improving LLMs in this context. For this, we evaluate three rarely-studied English dialects (Yorkshire, Geordie, and Cornish), plus African-American Vernacular English, and West Frisian as control. We find that human-human agreement when determining LLM generation quality directly impacts LLM-as-a-judge performance. That is, LLM-human agreement mimics the human-human agreement pattern, and so do metrics such as accuracy. It is an issue because LLM-human agreement measures an LLM's alignment with the human consensus; and hence raises questions about the feasibility of improving LLM performance in locales where low populations induce low agreement. We also note that fine-tuning does not eradicate, and might amplify, this pattern in English dialects. But also find encouraging signals, such as some LLMs' ability to generate high-quality data, thus enabling scalability. We argue that data must be carefully evaluated to ensure fair and inclusive LLM improvement; and, in the presence of scarcity, new tools are needed to handle the pattern found.

Yue Gong, Shanyuan Liu, Liuzhuozheng Li et al.

We proposed the Chinese Text Adapter-Flux (CTA-Flux). An adaptation method fits the Chinese text inputs to Flux, a powerful text-to-image (TTI) generative model initially trained on the English corpus. Despite the notable image generation ability conditioned on English text inputs, Flux performs poorly when processing non-English prompts, particularly due to linguistic and cultural biases inherent in predominantly English-centric training datasets. Existing approaches, such as translating non-English prompts into English or finetuning models for bilingual mappings, inadequately address culturally specific semantics, compromising image authenticity and quality. To address this issue, we introduce a novel method to bridge Chinese semantic understanding with compatibility in English-centric TTI model communities. Existing approaches relying on ControlNet-like architectures typically require a massive parameter scale and lack direct control over Chinese semantics. In comparison, CTA-flux leverages MultiModal Diffusion Transformer (MMDiT) to control the Flux backbone directly, significantly reducing the number of parameters while enhancing the model's understanding of Chinese semantics. This integration significantly improves the generation quality and cultural authenticity without extensive retraining of the entire model, thus maintaining compatibility with existing text-to-image plugins such as LoRA, IP-Adapter, and ControlNet. Empirical evaluations demonstrate that CTA-flux supports Chinese and English prompts and achieves superior image generation quality, visual realism, and faithful depiction of Chinese semantics.

Ishmanbir Singh, Dipankar Srirag, Aditya Joshi

Sarcasm is a challenge to sentiment analysis because of the incongruity between stated and implied sentiment. The challenge is exacerbated when the implication may be relevant to a specific country or geographical region. Pragmatic metacognitive prompting (PMP) is a cognition-inspired technique that has been used for pragmatic reasoning. In this paper, we harness PMP for explainable sarcasm detection for Australian and Indian English, alongside a benchmark dataset for standard English. We manually add sarcasm explanations to an existing sarcasm-labeled dataset for Australian and Indian English called BESSTIE, and compare the performance for explainable sarcasm detection for them with FLUTE, a standard English dataset containing sarcasm explanations. Our approach utilising PMP when evaluated on two open-weight LLMs (GEMMA and LLAMA) achieves statistically significant performance improvement across all tasks and datasets when compared with four alternative prompting strategies. We also find that alternative techniques such as agentic prompting mitigate context-related failures by enabling external knowledge retrieval. The focused contribution of our work is utilising PMP in generating sarcasm explanations for varieties of English.

Jingheng Ye, Shen Wang, Jiaqi Chen et al.

Large Language Models (LLMs) have transformed artificial intelligence, offering profound opportunities for educational applications. However, their ability to provide fine-grained educational feedback for K-12 English writing remains underexplored. In this paper, we challenge the error analysis and pedagogical skills of LLMs by introducing the problem of Fine-grained Error Analysis for English Learners and present the Fine-grained Error ANalysis for English Learners (FEANEL) Benchmark. The benchmark comprises 1,000 essays written by elementary and secondary school students, and a well-developed English writing error taxonomy. Each error is annotated by language education experts and categorized by type, severity, and explanatory feedback, using a part-of-speech-based taxonomy they co-developed. We evaluate state-of-the-art LLMs on the FEANEL Benchmark to explore their error analysis and pedagogical abilities. Experimental results reveal significant gaps in current LLMs' ability to perform fine-grained error analysis, highlighting the need for advancements in particular methods for educational applications.

A. A. Shirshikova

This article explores the semantics and usage of prepositions in the English that denote temporal limits of actions. A review of various lexicographical sources, reference literature, and grammars is conducted, highlighting that not all sources provide comprehensive information on the meanings and functioning of prepositions, often offering only general information. Practical material for the study is extracted from the British National Corpus, comprising approximately two thousand contexts. It is established that making a definitive conclusion about including a temporal limit within the timeframe allocated for an action is not always possible. This semantic ambiguity is noted in around 20% of the total number of analyzed contexts. The study demonstrates that to resolve ambiguity and ensure successful communication, addressees often resort to using clarifying elements or complete / partial paraphrasing of the message text. Clarifications are found to be most typical in texts of a scientific research nature, schedules, legal and economic documents. The article concludes on the necessity of further research related to the semantics and usage of prepositions.

Ya-Ling Huang, Sarah Thorning, Chun-Chih Lin et al.

Abstract Background Worldwide, the culturally and linguistically diverse (CALD) population is increasing, and is predicted to reach 405 million by 2050. The delivery of emergency care for the CALD population can be complex due to cultural, social, and language factors. The extent to which cultural, social, and contextual factors influence care delivery to patients from CALD backgrounds throughout their emergency care journey is unclear. Using a systematic approach, this review aims to map the existing evidence regarding emergency healthcare delivery for patients from CALD backgrounds and uses a social ecological framework to provide a broader perspective on cultural, social, and contextual influence on emergency care delivery. Methods The Joanna Briggs Institute (JBI) scoping review methodology will be used to guide this review. The population is patients from CALD backgrounds who received care and emergency care clinicians who provided direct care. The concept is healthcare delivery to patients from CALD backgrounds. The context is emergency care. This review will include quantitative, qualitative, and mixed-methods studies published in English from January 1, 2012, onwards. Searches will be conducted in the databases of CINAHL (EBSCO), MEDLINE (Ovid), Embase (Elsevier), SocINDEX (EBSCO), Scopus (Elsevier), and a web search of Google Scholar. A PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) flow diagram will be used to present the search decision process. All included articles will be appraised using the Mixed Methods Appraisal Tool (MMAT). Data will be presented in tabular form and accompanied by a narrative synthesis of the literature. Discussion Despite the increased use of emergency care service by patients from CALD backgrounds, there has been no comprehensive review of healthcare delivery to patients from CALD backgrounds in the emergency care context (ED and prehospital settings) that includes consideration of cultural, social, and contextual influences. The results of this scoping review may be used to inform future research and strategies that aim to enhance care delivery and experiences for people from CALD backgrounds who require emergency care. Systematic review registration This scoping review has been registered in the Open Science Framework https://doi.org/10.17605/OSF.IO/HTMKQ

Kenny Mendoza, Víctor Eduardo Villalobos-Daniel, Alejandra Jáuregui et al.

Abstract We developed a mobile application to promote healthy lifestyles and collect non-communicable disease (NCD) data in Mexico. Its theoretical foundations are supported by a framework-guided literature review. With design sprints, Scrum, Model-View-Controller, and Representational State Transfer architecture, we operationalized evidence-based nutrition/physical activity information into a crowdsourcing- and gamification-based application. The application was piloted for three months to monitor the response of 520 adults. Potential improvements were characterized, considering benchmarking, expert guidance, and standards. Salud Activa (English: Active Health) has two crowdsourcing modules: Nutritional scanner, scanning products' bar codes, providing nutritional data, and allowing new product registry feeding our databases; Surveys, comprising gradually-released NCD questions. Three intervention modules were generated: Drinks diary, a beverage assessment component to receive hydration recommendations; Step counter, monitoring users’ steps via Google Fit/Health—iOS; Metabolic Avatar, interconnecting modules and changing as a function of beverage and step records. The 3-month median of Salud Activa use was seven days (IQR = 3–12), up to 35% of participants completed a Survey section, and 157 food products were registered through Nutritional scanner. Better customization might benefit usability and user engagement. Quantitative and qualitative data will enhance Salud Activa’s design, user uptake, and efficacy in interventions delivered through this platform.

Avinash Anand, Kritarth Prasad, Chhavi Kirtani et al.

Large Language Models (LLMs) excel in linguistic tasks but struggle with mathematical reasoning, particularly in non English languages like Hindi. This research aims to enhance the mathematical reasoning skills of smaller, resource efficient open-source LLMs in both Hindi and English. We evaluate models like OpenHathi 7B, LLaMA-2 7B, WizardMath 7B, Mistral 7B, LLeMMa 7B, MAmmoTH 7B, Gemini Pro, and GPT-4 using zero-shot, few-shot chain-of-thought (CoT) methods, and supervised fine-tuning. Our approach incorporates curriculum learning, progressively training models on increasingly difficult problems, a novel Decomposition Strategy to simplify complex arithmetic operations, and a Structured Solution Design that divides solutions into phases. Our experiments result in notable performance enhancements. WizardMath 7B exceeds Gemini's accuracy on English datasets by +6% and matches Gemini's performance on Hindi datasets. Adopting a bilingual approach that combines English and Hindi samples achieves results comparable to individual language models, demonstrating the capability to learn mathematical reasoning in both languages. This research highlights the potential for improving mathematical reasoning in open-source LLMs.

Sawsan J. Al-Harbi, Fouad K. Gatea

After water, tea is the most consumed nutrient on the planet. However, black tea accounts for 78% of global tea consumption, while green tea accounts for only 20%. Except for flavored tea, all types of tea are made from the dried leaves of the tea bush. The type of tea is determined by the degree of oxidation of the leaves. Unoxidized tea leaves are used to make tea leaf, which is one of the less processed varieties of tea. It therefore, contains the most powerful antioxidants and beneficial polyphenols. Green tea polyphenols include epigallocatechin gallate (EGCG), epicatechin gallate, epicatechins, and flavanols, all of which are being studied in the lab for their potential in vivo effects. Kaempferol, quercetin, and myricetin are three types of flavonoids found in various parts. Although the caffeine in green tea can improve mental alertness, there is only weak, inconclusive evidence that it reduces the risk of most cancers or cardiovascular diseases, and there is no evidence that it aids weight loss. Using green tea as a health supplement has been linked to a slight improvement in general well-being. In a 2020 review, the Cochrane Collaboration identified a few potential negative effects, including gastrointestinal issues, higher levels of liver enzymes, and, more rarely, insomnia, elevated blood pressure, and skin reactions. Its anticancer and anti-inflammatory properties are well-known. Catechins are the main antioxidant dealers among the biologically active compounds found in Camellia sinesis. According to recent medical studies, the presence of function structural agencies and the range of hydroxyl agencies have a major impact on catechins' antioxidant activity. Unfermented inexperienced tea is the best source of those compounds. The review on green tea and its catechins focused on language literature in English. The literature search was conducted in the following databases: Pubmed (1997-2020), EMBASE (1997-2020), Allied and complementary Medicine Database (AMED, 1997-2020) and China Journals Full Text Database (1997-2020). The keywords used were selected from the following terms: green tea, catechins, anticancer, diabetes, polyphenols, in vivo studies, general pharmacology and toxicology. The health benefits and adverse effects of green tea and its catechins were reviewed. Keywords: Green Tea, Human, diseases, weight loss Citation: Al-Harbi SJ, Gatea FK. Therapeutic role of green tea on human body function, some diseases and weight loss: A review. Iraqi JMS. 2023; 21(1): 1-10. doi: 10.22578/IJMS.21.1.1

Sujata Sharma, Shabnam Joshi

Numerous studies conducted in the last few years have produced figures showing that the incidence of musculoskeletal issues is continuously rising and that a variety of treatment options are available. Musculoskeletal illnesses (MSDs), including fractures, arthritis, and osteoporosis, are increasingly treated with electromagnetic fields (EMFs). As a non-invasive, secure, and efficient treatment tool with no apparent side effects, Pulsed Electromagnetic field (PEMF) are well recognized. The present study aims to evaluate the literature by reviewing the data already available on PEMF's effectiveness in the treatment of different musculoskeletal disorders. For locating the literature articles published in English language on various musculoskeletal diseases treated by PEMFs were included. Information was looked for in the databases of PubMed, Google Scholar, Cochrane, and SCOPUS. The result of the study shows that due to its great efficacy and few risk considerations, PEMF has a lot of potentials to become a separate or complementary treatment strategy for treating numerous musculoskeletal disorders. The present study concludes that numerous issues are still unresolved. Further research from well-designed, high-quality studies are required to standardise therapy parameters and identify the most effective process for healthcare decision-making prior to widespread clinical application. In this study, we aim to provide up-to-date details on the therapeutic applications, mechanism of action, and ethical issues surrounding PEMFs in musculoskeletal disorders.

Amir Sartipi, Meghdad Dehghan, Afsaneh Fatemi

Nowadays, many researchers are focusing their attention on the subject of machine translation (MT). However, Persian machine translation has remained unexplored despite a vast amount of research being conducted in languages with high resources, such as English. Moreover, while a substantial amount of research has been undertaken in statistical machine translation for some datasets in Persian, there is currently no standard baseline for transformer-based text2text models on each corpus. This study collected and analysed the most popular and valuable parallel corpora, which were used for Persian-English translation. Furthermore, we fine-tuned and evaluated two state-of-the-art attention-based seq2seq models on each dataset separately (48 results). We hope this paper will assist researchers in comparing their Persian to English and vice versa machine translation results to a standard baseline.

Zedian Xiao, William Held, Yanchen Liu et al.

Large Language Models (LLMs) are trained on corpora disproportionally weighted in favor of Standard American English. As a result, speakers of other dialects experience significantly more failures when interacting with these technologies. In practice, these speakers often accommodate their speech to be better understood. Our work shares the belief that language technologies should be designed to accommodate the diversity in English dialects and not the other way around. However, prior works on dialect struggle with generalizing to evolving and emerging dialects in a scalable manner. To fill this gap, our method, HyperLoRA, leverages expert linguistic knowledge to enable resource-efficient adaptation via hypernetworks. By disentangling dialect-specific and cross-dialectal information, HyperLoRA improves generalization to unseen dialects in a task-agnostic fashion. Not only is HyperLoRA more scalable in the number of parameters, but it also achieves the best or most competitive performance across 5 dialects in a zero-shot setting. In this way, our approach facilitates access to language technology for billions of English dialect speakers who are traditionally underrepresented.

Vera Pavlova

In this work, we approach the problem of Qur'anic information retrieval (IR) in Arabic and English. Using the latest state-of-the-art methods in neural IR, we research what helps to tackle this task more efficiently. Training retrieval models requires a lot of data, which is difficult to obtain for training in-domain. Therefore, we commence with training on a large amount of general domain data and then continue training on in-domain data. To handle the lack of in-domain data, we employed a data augmentation technique, which considerably improved results in MRR@10 and NDCG@5 metrics, setting the state-of-the-art in Qur'anic IR for both English and Arabic. The absence of an Islamic corpus and domain-specific model for IR task in English motivated us to address this lack of resources and take preliminary steps of the Islamic corpus compilation and domain-specific language model (LM) pre-training, which helped to improve the performance of the retrieval models that use the domain-specific LM as the shared backbone. We examined several language models (LMs) in Arabic to select one that efficiently deals with the Qur'anic IR task. Besides transferring successful experiments from English to Arabic, we conducted additional experiments with retrieval task in Arabic to amortize the scarcity of general domain datasets used to train the retrieval models. Handling Qur'anic IR task combining English and Arabic allowed us to enhance the comparison and share valuable insights across models and languages.

Susan E. Smith, Nina Sivertsen, Lauren Lines et al.

Objectives: : Vaccine refusal is increasing in Australia and is a major concern in high- and middle-income countries. There is evidence to suggest that some parents, even those who elect to immunise, may be vaccine hesitant with some manipulating the schedule by excluding or delaying some vaccines. The aim of this review was to gain an understanding of factors that influence vaccine decision-making in pregnant women and parents of children. Design: : An integrative review approach was used to produce an analysis of existing literature on vaccine decision-making in pregnancy and parents. As the broadest of review methods, an integrative review can include a range of experimental and non-experimental research, thereby ensuring the inclusion of data from multiple perspectives. Data Sources: : Online databases were searched for research related to vaccine decision-making in pregnant women and parents. Original and review articles were sought that were published in English between 2015 and 2021. Reviewed articles included qualitative and quantitative studies and systematic reviews. No mixed methods papers were located or excluded from this review. Review methods: : The review method was an integrative review informed by Coughlan. Results: : Papers from thirteen predominantly high- and middle-income countries were selected for this review. A total of 31 articles fit the inclusion/exclusion criteria, including qualitative, quantitative and review articles. Three main themes were identified including the role of healthcare professionals, vaccine safety concerns and alternative influences. Alternative influences included: social media, friends and family, religion, conspiracy theories and salutogenic parenting. Findings suggest that high levels of anxiety are involved in vaccine decision-making with parents seeking information from multiple sources including healthcare professionals, friends and family and social media. Conclusions: : Pregnancy is an ideal time to provide education on both pregnancy and childhood vaccinations. However, some parents reported dissatisfaction in their therapeutic relationships with healthcare professionals. As a result, parents can resort to their own information seeking, in the main via social media which has been linked to vaccine refusal. Additionally, some healthcare professionals report feeling inadequately prepared for the role of immunisation promotion and provision. Parental information seeking from non-traditional sources has been shown to result in the acquisition of misinformation, exposure to conspiracy theories, the inevitable loss of vaccine confidence and subsequent vaccine refusal.

Caleb Ziems, William Held, Jingfeng Yang et al.

Dialect differences caused by regional, social, and economic factors cause performance discrepancies for many groups of language technology users. Inclusive and equitable language technology must critically be dialect invariant, meaning that performance remains constant over dialectal shifts. Current systems often fall short of this ideal since they are designed and tested on a single dialect: Standard American English (SAE). We introduce a suite of resources for evaluating and achieving English dialect invariance. The resource is called Multi-VALUE, a controllable rule-based translation system spanning 50 English dialects and 189 unique linguistic features. Multi-VALUE maps SAE to synthetic forms of each dialect. First, we use this system to stress tests question answering, machine translation, and semantic parsing. Stress tests reveal significant performance disparities for leading models on non-standard dialects. Second, we use this system as a data augmentation technique to improve the dialect robustness of existing systems. Finally, we partner with native speakers of Chicano and Indian English to release new gold-standard variants of the popular CoQA task. To execute the transformation code, run model checkpoints, and download both synthetic and gold-standard dialectal benchmark datasets, see http://value-nlp.org.

Ravinga Perera, Thilakshi Fonseka, Rashmini Naranpanawa et al.

The performance of Neural Machine Translation (NMT) depends significantly on the size of the available parallel corpus. Due to this fact, low resource language pairs demonstrate low translation performance compared to high resource language pairs. The translation quality further degrades when NMT is performed for morphologically rich languages. Even though the web contains a large amount of information, most people in Sri Lanka are unable to read and understand English properly. Therefore, there is a huge requirement of translating English content to local languages to share information among locals. Sinhala language is the primary language in Sri Lanka and building an NMT system that can produce quality English to Sinhala translations is difficult due to the syntactic divergence between these two languages under low resource constraints. Thus, in this research, we explore effective methods of incorporating Part of Speech (POS) tags to the Transformer input embedding and positional encoding to further enhance the performance of the baseline English to Sinhala neural machine translation model.

Parker T. Gordon

Shaykh Siddique, Tahmid Ahmed, Md. Rifayet Azam Talukder et al.

The applications of recurrent neural networks in machine translation are increasing in natural language processing. Besides other languages, Bangla language contains a large amount of vocabulary. Improvement of English to Bangla machine translation would be a significant contribution to Bangla Language processing. This paper describes an architecture of English to Bangla machine translation system. The system has been implemented with the encoder-decoder recurrent neural network. The model uses a knowledge-based context vector for the mapping of English and Bangla words. Performances of the model based on activation functions are measured here. The best performance is achieved for the linear activation function in encoder layer and the tanh activation function in decoder layer. From the execution of GRU and LSTM layer, GRU performed better than LSTM. The attention layers are enacted with softmax and sigmoid activation function. The approach of the model outperforms the previous state-of-the-art systems in terms of cross-entropy loss metrics. The reader can easily find out the structure of the machine translation of English to Bangla and the efficient activation functions from the paper.

Toshiko Shibano, Xinyi Zhang, Mia Taige Li et al.

To address the performance gap of English ASR models on L2 English speakers, we evaluate fine-tuning of pretrained wav2vec 2.0 models (Baevski et al., 2020; Xu et al., 2021) on L2-ARCTIC, a non-native English speech corpus (Zhao et al., 2018) under different training settings. We compare \textbf{(a)} models trained with a combination of diverse accents to ones trained with only specific accents and \textbf{(b)} results from different single-accent models. Our experiments demonstrate the promise of developing ASR models for non-native English speakers, even with small amounts of L2 training data and even without a language model. Our models also excel in the zero-shot setting where we train on multiple L2 datasets and test on a blind L2 test set.

Simin Anbarshahi, Lida Sharafati

In an attempt to contribute to the ongoing debate about how output tasks affect noticing of linguistic forms, the present study set out to investigate the effect of pushed output tasks on grammatical accuracy in sentence writing of Iranian EFL learners. Fifty homogenous Iranian EFL learners were randomly assigned to two experimental and control groups. Then, every group underwent ten different treatment sessions. The control group received writing instruction through conventional methods, while the experimental group received instruction through two pushed output tasks. In the case of the experimental group, in the first five treatment sessions, four grammatical structures were presented through picture cued tasks. The next five treatment sessions directed at other structures took place via reconstruction tasks. Two different versions of the writing section of the Preliminary English Test (PET) were used as pre/post-test. The results indicated that the experimental group significantly outperformed the control group. Therefore, it might be argued that pushed output-based tasks had a positive effect on the Iranian EFL learner’s grammatical accuracy in sentence writing. These findings provide empirical support for the output hypothesis and have pedagogical implications for the choice of output-oriented grammar tasks.