Terms Of Recognition Research Articles

Self-augmented sequentiality-aware encoding for aspect term extraction

Aspect Term Extraction (ATE) is a natural language processing task which recognizes and extracts aspect terms from sentences. The recent study in this field successfully leverages Pretrained Language Model (PLM) and data augmentation, which contributes to the construction of knowledgeable encoder for ATE. In this paper, we propose a novel method to strengthen ATE encoder, using self-augmented mechanism and sequentiality-aware network. Specifically, self augmentation expands training data with paraphrases and fuses correlated information using PLM during encoding. Back translation is used for obtaining pragmatically-diverse paraphrases. On the basis, BiGRU is utilized as a supplementary neural layer for extra-encoding, so as to involve sequence features into the output hidden states of PLM. We refer to our method as Self-augmented Sequentiality-sensitive Encoding (SSE for short). We carry out experiments on the benchmark SemEval datasets, including L-14, R-14, R-15 and R-16. Experimental results show that SSE yields substantial improvements, compared to BERT-based baselines. In particular, it is demonstrated that SSE is able to collaborate with other data augmentation approaches to produce more significant improvements, where the resultant ATE performance is up to 86.74%, 88.91%, 77.43% and 82.42% F1-scores (for L-14, R-14, R-15 and R-16 respectively).

Deep Learning-Based Aspect Term Extraction for Sentiment Analysis in Hindi

Objectives: Aspect terms play a vital role in finalizing the sentiment of a given review. This experimental study aims to improve the aspect term extraction mechanism for Hindi language reviews. Methods: We trained and evaluated a deep learning-based supervised model for aspect term extraction. All experiments are performed on a well-accepted Hindi dataset. A BiLSTM-based attention technique is employed to improve the extraction results. Findings: Our results show better F-score results than many existing supervised methods for aspect term extraction. Accuracy results are outstanding compared to other reported results. Results showed an outstanding 91.27% accuracy and an F–score of 43.16. Novelty: This proposed architecture and the achieved results are a foundational resource for future studies and endeavours in the field. Keywords: Sentiment analysis, Aspect based sentiment analysis, Aspect term extraction, Deep Learning, Bi LSTM, Indian language, Hindi

Utilization of Suji Leaves Extract (Pleomele Angustifolia N.E Brown) in Inhibiting Carrageenan-Induced Inflammation on Rats

Suji leaf (Pleomele angustifolia N.E. Brown) has long been used as an ingredient for traditional medicines. This study seeks to evaluate the anti-inflammatory activity of suji leaf extract in terms of its ability to reduce oedema in the hind paws of rats. Six groups were treated: negative control, positive control given diclofenac sodium as anti-inflammatory medication, two groups of suji leaf extract powder (SEP) with doses of 300 and 800 mg/kg, acetone extract of suji leaf (AES), and a group of acetone extract of SEP (EA-SEP) at a dose of 500 mg/kg with oral administration. Injections of 1% carrageenan suspension into the right hind paw of rats induced inflammation. The results demonstrated that SEP administered at a dose of 800 mg/kg has an inflammatory capacity (80.56%), AES (56.94%), and AE-SEP (75.7%). Chlorophyll, total phenol, and antioxidant capacity in SEP (9.0809 mg /g sample; 3.7354 mg GAE/g sample; 3.04 mg AAE/g sample), AES (4.6471 mg /g sample; 0.9994 mg GAE/g sample; 3.26 mg AAE/g sample), and AE-SEP (6.4912 mg /g sample; 2.1703 mg GAE/g sample; 2.55 mg AAE/g sample). According to qualitative test results, Suji extract contains bioactive compounds of the flavonoid group, saponins, steroids, and triterpenoids. It is believed that phenolic compounds function as anti-inflammatory agents.

Harnessing the power of AutoML: A comparative study of image recognition techniques for smoking detection

As infrastructure continues to evolve, the significance of fire protection escalates. Many fires are caused by smoking in smoke-free areas, underscoring the necessity to promptly detect smoking activities in hazardous zones. In this scenario, image recognition emerges as a pivotal tool. The accuracy and efficiency of image recognition bear substantial implications for both academic and industrial sectors, and these aspects form the crux of our investigation. This study aims to compare the performance of image recognition techniques based on automatic machine learning with those of traditional methods such as YOLO. Our findings indicate that image recognition powered by automatic machine learning outperforms YOLO recognition in terms of efficiency and accuracy.

Machine-Learning-Based Approaches for Multi-Level Sentiment Analysis of Romanian Reviews

Sentiment analysis has increasingly gained significance in commercial settings, driven by the rising impact of reviews on purchase decision-making in recent years. This research conducts a thorough examination of the suitability of machine learning and deep learning approaches for sentiment analysis, using Romanian reviews as a case study, with the aim of gaining insights into their practical utility. A comprehensive, multi-level analysis is performed, covering the document, sentence, and aspect levels. The main contributions of the paper refer to the in-depth exploration of multiple sentiment analysis models at three different textual levels and the subsequent improvements brought with respect to these standard models. Additionally, a balanced dataset of Romanian reviews from twelve product categories is introduced. The results indicate that, at the document level, supervised deep learning techniques yield the best outcomes (specifically, a convolutional neural network model that obtains an AUC value of 0.93 for binary classification and a weighted average F1-score of 0.77 in a multi-class setting with 5 target classes), albeit with increased resource consumption. Favorable results are achieved at the sentence level, as well, despite the heightened complexity of sentiment identification. In this case, the best-performing model is logistic regression, for which a weighted average F1-score of 0.77 is obtained in a multi-class polarity classification task with three classes. Finally, at the aspect level, promising outcomes are observed in both aspect term extraction and aspect category detection tasks, in the form of coherent and easily interpretable word clusters, encouraging further exploration in the context of aspect-based sentiment analysis for the Romanian language.

Enhancing CAT education: the significance of teaching the right skills in the right time

This article explores the dynamic landscape of Computer-Assisted Translation (CAT) tools, aiming to identify the key skills employed by language professionals and the essential competencies students should acquire. Employing a survey methodology, responses from a diverse pool of translators shed light on CAT tool preferences, termbase utilization, and automation practices. RWS Trados and memoQ emerge as frontrunners, underlining the versatility required in contemporary translation workflows. While over 80% adopt quality assurance features and ensure precise tag transfers, challenges persist in reusing termbases across projects.ile conversion skills, particularly.tmx conversions, prove significant for translation memory management. Automation practices such as term extraction and pretranslation reveal varied adoption, signaling opportunities for tailored education. Despite limited current usage, machine translation plug-ins and AI present strategic advantages for translators in training, with the emergence of technologies like ChatGPT anticipated to drive a surge in usage Encouragingly, the article concludes that the emergence of AI does not diminish CAT tool usage, positioning them as integral to the evolving language services landscape.

Multi-modal online review driven product improvement design based on scientific effects knowledge graph

Online reviews serve as significant channels for users to express their preferences, constituting an essential data source for enterprises to identify product requirements. However, with the widespread adoption of smartphones, the act of capturing spontaneous photographs has become a habitual practice for the majority, resulting in the increasing prevalence of supplementary visual expressions within online reviews. Therefore, an important research question emerges: How can product requirements be effectively extracted from multimodal online reviews and subsequently translated into product design proposals? In this paper, we establish a framework, seamlessly integrating aspect-based sentiment analysis, product requirement identification, and requirement mapping based on a scientific effect knowledge graph. Firstly, we conduct aspect term extraction on the online reviews, followed by aspect sentiment classification. Subsequently, we delve deeper into the analyzed results obtained from aspect-based sentiment analysis to identify preferences in product requirements. Finally, we employ requirement mapping based on a scientific effect knowledge graph to generate proposals for product design improvements. To validate the efficacy of our approach, we conducted experiments and the results demonstrate that our method outperforms alternative approaches, while the requirement mapping based on a scientific effect knowledge graph efficiently facilitates the realisation of product design improvements.

Evaluation of Polyphenolic Profile and Antioxidant Activity of Sea Buckthorn (Elaeagnus rhamnoides (L.) A. Nelson) Leaf and Berry Extracts Obtained via Optimized Microwave-Assisted and Accelerated Solvent Extraction

The aim of this study was to optimize parameters of microwave-assisted extraction (MAE) and accelerated solvent extraction (ASE) in terms of extraction temperature and time, microwave power and cycle numbers on the phenolic content of sea buckthorn leaves and berries, using 70% ethanol (v/v) as an extraction solvent. The characterization of phenolic composition in leaf and berry extracts obtained at optimal MAE and ASE conditions was performed with UPLC/ESI-MS2, while antioxidant activity was determined using the ORAC method. The optimal extraction conditions for MAE were 60 °C, 500 W and 15 min for leaves and 60 °C, 300 W, and 10 min for berries. The optimal extraction conditions for ASE from both leaves and berries were 120 °C, 15 min, and 3 cycles. Total phenolic content (TPC) in MAE and ASE extracts from leaves was similar to the TPC determined in extracts obtained by conventional extraction (60 °C/30 min); however, ASE contributed to the higher TPC of the berry extracts. The flavonols kaempferol-3-rutinoside in the leaves and kaempferol in the berries were the most abundant phenols of sea buckthorn. A higher antioxidant activity was found in the leaf extracts obtained by ASE and it correlated with the phenolic content. In general, ASE favored the extraction of all polyphenols from leaves, while MAE was more suitable for the extraction of flavonols from berries, suggesting that the choice of the optimal extraction method is crucial with regard to the target molecules and future applications.

Dispersive liquid-liquid microextraction as a novel enrichment approach for compound-specific carbon isotope analysis of chlorinated phenols.

Compound-specific isotope analysis (CSIA) via gas chromatography-isotope ratio mass spectrometry (GC-IRMS) is a potent tool to elucidate the fate of (semi-)volatile organic contaminants in technical and environmental systems. Yet, due to the comparatively low sensitivity of IRMS, an enrichment step prior to analysis often is inevitable. A promising approach for fast as well as economic analyte extraction and preconcentration prior to CSIA is dispersive liquid-liquid microextraction (DLLME) - a well-established technique in concentration analysis of contaminants from aqueous samples. Here, we present and evaluate the first DLLME method for GC-IRMS exemplified by the analysis of chlorinated phenols (4-chlorophenol, 2,4-dichlorophenol, and 2,4,6-trichlorophenol) as model compounds. The analytes were simultaneously acetylated with acetic anhydride and extracted from the aqueous phase using a binary solvent mixture of acetone and tetrachloroethylene. With this method, reproducible δ13C values were achieved with errors ≤ 0.6‰ (n = 3) for aqueous concentrations down to 100 μg L-1. With preconcentration factors between 130 and 220, the method outperformed conventional liquid-liquid extraction in terms of sample preparation time and resource consumption with comparable reproducibility. Furthermore, we have demonstrated the suitability of the method (i) for the extraction of the analytes from a spiked river water sample and (ii) to quantify kinetic carbon isotope effect for 2,4,6-trichlorophenol during reduction with zero-valent zinc in a laboratory batch experiment. The presented work shows for the first time the potential of DLLME for analyte enrichment prior to CSIA and paves the way for further developments, such as the extraction of other compounds or scaling up to larger sample volumes.

Part-of-speech based label update network for aspect sentiment triplet extraction

Aspect sentiment triplet analysis (ASTE) is a nuanced task that entails the extraction of all triplets from a user comment, where each triplet consist of an aspect term, an opinion term, and the associated sentiment polarity of the aspect term. Recent research has brought forth a boundary-driven table-filling approach that adeptly tackles the persistent issues of inconsistent relationships and boundary insensitivity found in prior methods, but the improvement in performance is somewhat limited because this method overlook the wealth of information encapsulated within each word present in the sentence. To overcome these limitations, this study proposes a novel Part-of-speech Based Label Update Network (PBLUN) for aspect sentiment triplet extraction. Specifically, a POS-based label update module integrated with aspect term extraction (ATE) and opinion term extraction (OTE) tasks is devised to discern the existence of aspect or opinion words within the set adjacent search domain and update their labels. In addition, the proposed model leverages biaffine attention network to extract probability distribution denoting various relationships between words and effectively combine them with relation-level representation. Experiments conducted on four benchmark datasets have conclusively demonstrated the advantages of our proposed method when compared to strong baseline models.

Understanding Fine-Grained Sentiments of Super-Priority Destination Visitors using Multi-task Learning for Extraction of Aspect Terms and Polarity Classification on Reviews

One sector that plays an important role in the national economy is the Tourism sector. To maintain economic stability, the Indonesian Government has made various efforts to mitigate the impact of the Covid-19 pandemic on the tourism sector. The National Economic Recovery (PEN) is one of its programs, specifically focused on the recovery of tourism, particularly in the 5 super-priority destinations (Lake Toba, Borobudur, Mandalika, Labuan Bajo, Likupang). To ensure the effective recovery of these 5 super-priority destinations, in addition to information from stakeholders, the government can conduct studies based on the aspirations of the people. One task that can assist the government in summarizing user reviews is sentiment analysis. Previous studies have focused on comments from the local Indonesian population, which have not reached the majority of tourists who comment in English. Therefore, there is a need for Sentiment Analysis (SA) at the aspect level on TripAdvisor reviews of the Super Priority Destinations (SPDs) using the English language. The method used for sentiment analysis of these tourist reviews is the Local Context Focus - Aspect Term Extraction & Aspect Polarization Classification (LCF-ATEPC). This method employs multi-task learning, domain Bidirectional Encoder Representations from Transformers (BERT), and information about the aspect position within a sentence. Based on the research, the LCF-ATEPC model has proven to be capable of performing sentiment analysis of English aspects effectively. The best-performing LCF-ATEPC model was obtained using a dataset without outliers (95%) with APC-ACC, APC-F1, and ATE-F1 accuracies of 83.33%, 69.5%, and 66.83%, respectively.

Context-Aware Dynamic Word Embeddings for Aspect Term Extraction

The aspect term extraction (ATE) task aims to extract aspect terms describing a part or an attribute of a product from review sentences. Most existing works rely on either general or domain embedding to address this problem. Despite the promising results, the importance of general and domain embeddings is still ignored by most methods, resulting in degraded performances. Besides, word embedding is also related to downstream tasks, and how to regularize word embeddings to capture context-aware information is an unresolved problem. To solve these issues, we first propose context-aware dynamic word embedding (CDWE), which could simultaneously consider general meanings, domain-specific meanings, and the context information of words. Based on CDWE, we propose an attention-based convolution neural network, called ADWE-CNN for ATE, which could adaptively capture the previous meanings of words by utilizing an attention mechanism to assign different importance to the respective embeddings. The experimental results show that ADWE-CNN achieves a comparable performance with the state-of-the-art approaches. Various ablation studies have been conducted to explore the benefit of each component. Our code is publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">http://github.com/xiejiajia2018/ADWE-CNN</uri> .

CuXCMP: CUDA-Accelerated Private Comparison Based on Homomorphic Encryption

Private comparison schemes constructed on homomorphic encryption offer the noninteractive and parallelizable features, and have advantages in communication bandwidth and performance. In this work, we propose cuXCMP, an extension of the privacy comparison scheme XCMP (AsiaCCS 2018). We address the relatively small input domain and the incompletely expressible output of XCMP, by modifying the encoding method and devising a constant term extraction (CTX) approach. Then, we describe a method for constructing privacy-preserving decision tree (PPDT) using this scheme. Considering the high computational overhead of CTX, we exploit the massive parallelism of the GPU to accelerate this function. Based on the results of the kernel profiling, we utilize several optimization techniques to improve the performance, including using multiple CUDA streams, reducing the grid dimension, kernel fusion, etc. By accelerating this function, we boost the execution time of the scheme and demonstrate 130× and 1.9× speedups for CTX and cuXCMP, respectively, as well as a 35% reduction in the evaluation time of PPDT.

Evaluation of the effect of Musa paradisiaca L. rhizome on Saccharomyces glucose absorption and DPPH free radical scavenging capacity

Introduction: Musa paradisiaca is a common edible plant used in traditional medical systems for its medicinal properties. In this study, in vitro anti-hyperglycaemic potential and in vitro antioxidant activity of M. paradisiaca rhizome were investigated. Methods: Dried rhizome of M. paradisiaca was sequentially extracted to hexane and dichloromethane using cold maceration technique. Stock concentrations of hexane extract (35.35 mg/mL) and dichloromethane extract (22.14 mg/mL) were diluted to prepare different concentrations and were used to evaluate the effects of plant extracts on glucose uptake potential by yeast cells and DPPH free radical scavenging capacity compared to metformin and ascorbic acid standards respectively. Results: The extracts improved the glucose uptake through yeast plasma membrane, since a linear relationship in glucose uptake by yeast cells wasobserved with gradual increase in concentration of the plant extract. In terms of glucose adsorption capacity, dichloromethane extract of plant possessed a significant (p&lt;0.05) activity compared to the hexane extract at higher glucose concentrations, but this activity was significantly less compared to metformin standard (p&lt;0.05). Further, dichloromethane extract demonstrated a higher level of glucose adsorption potential than hexane extract. Same extract had the highest DPPH radical scavenging potential in antioxidant assay. However, this activity was concentration-dependent, and both extracts showed lower radical scavenging potentials compared to the ascorbic acid standard. Conclusion: Dichloromethane extract of M. paradisiaca rhizome is more biologically active compared to its hexane extract in terms of in vitro glucose adsorption potential and antioxidant properties. However, both extracts showed significantly lower activity compared to metformin in glucose uptake assay while ascorbic acid showed the highest activity in free radical scavenging.&#x0D; Keywords: DPPH, Glucose adsorption, Musa paradisiaca rhizome, Saccharomyces

Türkiye’den Toplanan Inula graveolens (L.) Desf. Türünün Bazı Biyolojik Aktivitelerinin Araştırılması

In this study, it was aimed to determine the phenolic and flavonoid content and different biological activities (antioxidant, enzyme inhibitor, anthelmintic) of the methanol extract of Inula graveolens (L.) Desf collected from Muğla (Turkey). As a result of the study, the total phenolic content was determined as 5.36±0.32 mg GAE/g, and the total flavonoid amount was determined as 3.49±0.05 mg QE/g extract equivalent. In the ß-carotene/linoleic acid method, the extract showed lower activity than the standard BHA used. The extract was determined to be equivalent to 4.28±0.24/0.47±0.03 mg TE/g extract in terms of copper and iron-reducing power capacity, respectively. Although the enzyme inhibitory activities of the extract increased with the increase in concentration, it was determined that it had lower activity than galantamine (89.41±0.05%) and kojic acid (73.93±0.10%) used as standard. Paralysis and death times of the extract at different concentrations (2.5,5,10,20 mg/mL) on Tubifex tubifex worms were determined. It was determined that the extract at high concentrations (20 mg/mL) exhibited an activity near that of andazole (10 mg/mL) used as a standard. According to these results, I. graveolens can be considered a good resource for the pharmaceutical industry due to its activities.

Natural history of rare diseases using natural language processing of narrative unstructured electronic health records: The example of Dravet syndrome.

The increasing implementation of electronic health records allows the use of advanced text-mining methods for establishing new patient phenotypes and stratification, and for revealing outcome correlations. In this study, we aimed to explore the electronic narrative clinical reports of a cohort of patients with Dravet syndrome (DS) longitudinally followed at our center, to identify the capacity of this methodology to retrace natural history of DS during the early years. We used a document-based clinical data warehouse employing natural language processing to recognize the phenotype concepts in the narrative medical reports. We included patients with DS who have a medical report produced before the age of 2 years and a follow-up after the age of 3 years ("DS cohort," 56 individuals). We selected two control populations, a "general control cohort" (275 individuals) and a "neurological control cohort" (281 individuals), with similar characteristics in terms of gender, number of reports, and age at last report. To find concepts specifically associated with DS, we performed a phenome-wide association study using Cox regression, comparing the reports of the three cohorts. We then performed a qualitative analysis of the surviving concepts based on their median age at first appearance. A total of 76 concepts were prevalent in the reports of children with DS. Concepts appearing during the first 2 years were mostly related with the epilepsy features at the onset of DS (convulsive and prolonged seizures triggered by fever, often requiring in-hospital care). Subsequently, concepts related to new types of seizures and to drug resistance appeared. A series of non-seizure-related concepts emerged after the age of 2-3 years, referring to the nonseizure comorbidities classically associated with DS. The extraction of clinical terms by narrative reports of children with DS allows outlining the known natural history of this rare disease in early childhood. This original model of "longitudinal phenotyping" could be applied to other rare and very rare conditions with poor natural history description.

Uncovering Sustainability Insights from Amazon’s Eco-Friendly Product Reviews for Design Optimization

This research investigates consumer reviews of eco-friendly products on Amazon to uncover valuable sustainability insights that can inform design optimization. Using natural language processing (NLP) techniques, including sentiment analysis, key terms extraction, and topic modeling, this research reveals diverse perspectives related to sustainability aspects in eco-friendly products. Innovatively, we integrate the NLP approach with correspondence analysis (CA) to understand consumer sentiments and preferences related to sustainability aspects. Leveraging CA, we visualize the interplay between eco-friendly product features and consumer sentiments, revealing underlying relationships and patterns. The CA biplot showcases the alignment of specific sustainability attributes with consumer satisfaction, highlighting which sustainability aspects hold greater influence over overall product ratings. As sustainability becomes an increasingly crucial aspect of consumer choices, our paper emphasizes the significance of a multidimensional approach that embraces both qualitative and quantitative insights. By blending CA with consumer reviews, we equip designers and stakeholders with an innovative and comprehensive toolkit to enhance sustainable design practices, paving the way for more informed and effective product development strategies in the realm of eco-friendliness.

Exploring the Lexis of Art Through a Specialized Corpus: A Bilingual Italian-English Perspective

This study presents an application of a specialized corpus, including texts specifically related to art and cultural heritage, to the analysis of artistic vocabulary in a bilingual (Italian-English) perspective, focusing on the Italian lemmas opera, figura and disegno and their English translation equivalents. The starting point is the Italian corpus that is being developed under the research project Lessico multilingue dei beni culturali (&amp;lsquo;Multilingual art and cultural heritage vocabulary&amp;rsquo;, LBC), available online in open access through NoSketchEngine. First, a lemmatized nounlist ordered by frequency of occurrence is extracted from the corpus, leading to the selection of the above-mentioned focus words, in view of both their frequency and status as technical terms within the domain of art (though exhibiting different levels of technicality). These are further investigated by extracting collocates and KWIC concordances, leading to the identification of several specialized collocations and domain-specific senses. The analysis subsequently moves from corpus to dictionary, exploring the extent to which the patterns emerging from corpus investigation are accounted for in the entries for opera, figura and disegno in four Italian-English bilingual dictionaries. From this viewpoint, the study also aims to show how specialized corpus data can be used for the extraction of collocations, terms, and context-specific word senses, which may in turn be used both to enrich the information provided by currently available general dictionaries, and to work towards the creation of a large-scale specialized bilingual dictionary, which is non-existent to date.

Splitting Hairs: Designing Corpus-Driven Hairstyling Glossary Entries for a Diverse Audience

This paper illustrates a bilingual corpus-driven term extraction and description procedure (Bowker &amp;amp; Pearson, 2002) in the popular field of hairdressing. We present examples of term entries (fringe, texture, to wear) derived from ad-hoc corpora compiled on the SketchEngine platform (about 200,000 words total), focusing on translation equivalents and phraseologies. We also consider the advantages of such lexical explorations vis-&amp;agrave;-vis the information available in professional publications. We finally present a proposal for the identification and design of terminological entries in a multimodal glossary, which should be comprehensive in content and adaptable to the needs of native and non-native speakers, professionals and laypeople.

Corpus linguistics and generative AI tools in term extraction: a case of Kashubian – a low-resource language

Electronic corpora have been an indispensable resource in a variety of language studies, including linguistics, lexicography or terminology. Provided that they are compiled in a systematic manner, such text collections can provide high quality data that can be readily used in a specific study or can be directly applied to a specific practical project. However, the creation of a usable corpus depends on the availability and the quality of source texts and the tools that are used for its processing. Another factor that often plays a significant role in successful ad hoc applications of corpora is their immediate accessibility. Recent developments in generative artificial intelligence (GenAI) have rendered the idea of instantaneous access to language data a feasible possibility. This paper discusses the results of a study into the feasibility of applying modern corpus and GenAI tools in the extraction of biological terminology in Kashubian, a regional language spoken in the north-central part of Poland (Kashubia). The overarching goal was to identify modern and effective tools that could be used by terminologists, lexicographers, translators, and teachers of Kashubian.