Computers

Research

Jump to: Review

21 pages, 1847 KB

Open AccessArticle

NewsSumm: The World’s Largest Human-Annotated Multi-Document News Summarization Dataset for Indian English

by Manish Motghare, Megha Agarwal and Avinash Agrawal

Computers 2025, 14(12), 508; https://doi.org/10.3390/computers14120508 - 23 Nov 2025

Viewed by 961

Abstract

The rapid growth of digital journalism has heightened the need for reliable multi-document summarization (MDS) systems, particularly in underrepresented, low-resource, and culturally distinct contexts. However, current progress is hindered by a lack of large-scale, high-quality non-Western datasets. Existing benchmarks—such as CNN/DailyMail, XSum, and [...] Read more.

The rapid growth of digital journalism has heightened the need for reliable multi-document summarization (MDS) systems, particularly in underrepresented, low-resource, and culturally distinct contexts. However, current progress is hindered by a lack of large-scale, high-quality non-Western datasets. Existing benchmarks—such as CNN/DailyMail, XSum, and MultiNews—are limited by language, regional focus, or reliance on noisy, auto-generated summaries. We introduce NewsSumm, the largest human-annotated MDS dataset for Indian English, curated by over 14,000 expert annotators through the Suvidha Foundation. Spanning 36 Indian English newspapers from 2000 to 2025 and covering more than 20 topical categories, NewsSumm includes over 317,498 articles paired with factually accurate, professionally written abstractive summaries. We detail its robust collection, annotation, and quality control pipelines, and present extensive statistical, linguistic, and temporal analyses that underscore its scale and diversity. To establish benchmarks, we evaluate PEGASUS, BART, and T5 models on NewsSumm, reporting aggregate and category-specific ROUGE scores, as well as factual consistency metrics. All NewsSumm dataset materials are openly released via Zenodo. NewsSumm offers a foundational resource for advancing research in summarization, factuality, timeline synthesis, and domain adaptation for Indian English and other low-resource language settings. Full article

(This article belongs to the Special Issue Natural Language Processing (NLP) and Large Language Modelling (2nd Edition))

► Show Figures

Figure 1

22 pages, 687 KB

Open AccessArticle

MacHa: Multi-Aspect Controllable Text Generation Based on a Hamiltonian System

by Delong Xu, Min Lin and Yurong Wang

Computers 2025, 14(12), 503; https://doi.org/10.3390/computers14120503 - 21 Nov 2025

Viewed by 325

Abstract

Multi-faceted controllable text generation can be viewed as an extension and combination of controllable text generation tasks. It requires the generation of fluent text while controlling multiple different attributes (e.g., negative emotions and environmental protection in themes). Current research either estimates compact latent [...] Read more.

Multi-faceted controllable text generation can be viewed as an extension and combination of controllable text generation tasks. It requires the generation of fluent text while controlling multiple different attributes (e.g., negative emotions and environmental protection in themes). Current research either estimates compact latent spaces for multiple attributes, reducing interference between different attributes but making it difficult to control the balance between multiple attributes, or controls the balance between multiple attributes but requires complex searches for decoding. Based on these issues, we propose a new method called MacHa, which trains an attribute latent space using multiple loss functions and establishes a mapping between the attribute latent space and attributes in sentences using a VAE network. An energy model based on the Hamilton function is defined in the potential space to control the balance between multiple attributes. Subsequently, in order to reduce the complexity of the decoding process, we extract samples using the RL sampling method and send them to the VAE decoder to generate the final text. The experimental results show that the MacHa method generates text with higher accuracy than the baseline models after balancing multiple attributes and has a fast decoding speed. Full article

(This article belongs to the Special Issue Natural Language Processing (NLP) and Large Language Modelling (2nd Edition))

► Show Figures

Figure 1

19 pages, 1791 KB

Open AccessArticle

Document Encoding Effects on Large Language Model Response Time and Consistency

by Dianeliz Ortiz Martes and Nezamoddin N. Kachouie

Computers 2025, 14(11), 493; https://doi.org/10.3390/computers14110493 - 13 Nov 2025

Viewed by 479

Abstract

Large language models (LLMs) such as GPT-4 are increasingly integrated into research, industry, and enterprise workflows, yet little is known about how input file formats shape their outputs. While prior work has shown that formats can influence response time, the effects on readability, [...] Read more.

Large language models (LLMs) such as GPT-4 are increasingly integrated into research, industry, and enterprise workflows, yet little is known about how input file formats shape their outputs. While prior work has shown that formats can influence response time, the effects on readability, complexity, and semantic stability remain underexplored. This study systematically evaluates GPT-4’s responses to 100 queries drawn from 50 academic papers, each tested across four formats, TXT, DOCX, PDF, and XML, yielding 400 question–answer pairs. We have assessed two aspects of the responses to the queries: first, efficiency quantified by response time and answer length, and second, linguistic style measured by readability indices, sentence length, word length, and lexical diversity where semantic similarity was considered to control for preservation of semantic context. Results show that readability and semantic content remain stable across formats, with no significant differences in Flesch–Kincaid or Dale–Chall scores, but response time is sensitive to document encoding, with XML consistently outperforming PDF, DOCX, and TXT in the initial experiments conducted in February 2025. Verbosity, rather than input size, emerged as the main driver of latency. However, follow-up replications conducted several months later (October 2025) under the updated Microsoft Copilot Studio (GPT-4) environment showed that these latency differences had largely converged, indicating that backend improvements, particularly in GPT-4o’s document-ingestion and parsing pipelines, have reduced the earlier disparities. These findings suggest that the file format matters and affects how fast the LLMs respond, although its influence may diminish as enterprise-level AI systems continue to evolve. Overall, the content and semantics of the responses are fairly similar and consistent across different file formats, demonstrating that LLMs can handle diverse encodings without compromising response quality. For large-scale applications, adopting structured formats such as XML or semantically tagged HTML can still yield measurable throughput gains in earlier system versions, whereas in more optimized environments, such differences may become minimal. Full article

(This article belongs to the Special Issue Natural Language Processing (NLP) and Large Language Modelling (2nd Edition))

► Show Figures

Figure 1

47 pages, 3137 KB

Open AccessArticle

DietQA: A Comprehensive Framework for Personalized Multi-Diet Recipe Retrieval Using Knowledge Graphs, Retrieval-Augmented Generation, and Large Language Models

by Ioannis Tsampos and Emmanouil Marakakis

Computers 2025, 14(10), 412; https://doi.org/10.3390/computers14100412 - 29 Sep 2025

Cited by 1 | Viewed by 1795

Abstract

Recipes available on the web often lack nutritional transparency and clear indicators of dietary suitability. While searching by title is straightforward, exploring recipes that meet combined dietary needs, nutritional goals, and ingredient-level preferences remains challenging. Most existing recipe search systems do not effectively [...] Read more.

Recipes available on the web often lack nutritional transparency and clear indicators of dietary suitability. While searching by title is straightforward, exploring recipes that meet combined dietary needs, nutritional goals, and ingredient-level preferences remains challenging. Most existing recipe search systems do not effectively support flexible multi-dietary reasoning in combination with user preferences and restrictions. For example, users may seek gluten-free and dairy-free dinners with suitable substitutions, or compound goals such as vegan and low-fat desserts. Recent systematic reviews report that most food recommender systems are content-based and often non-personalized, with limited support for dietary restrictions, ingredient-level exclusions, and multi-criteria nutrition goals. This paper introduces DietQA, an end-to-end, language-adaptable chatbot system that integrates a Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and a Large Language Model (LLM) to support personalized, dietary-aware recipe search and question answering. DietQA crawls Greek-language recipe websites to extract structured information such as titles, ingredients, and quantities. Nutritional values are calculated using validated food composition databases, and dietary tags are inferred automatically based on ingredient composition. All information is stored in a Neo4j-based knowledge graph, enabling flexible querying via Cypher. Users interact with the system through a natural language chatbot friendly interface, where they can express preferences for ingredients, nutrients, dishes, and diets, and filter recipes based on multiple factors such as ingredient availability, exclusions, and nutritional goals. DietQA supports multi-diet recipe search by retrieving both compliant recipes and those adaptable via ingredient substitutions, explaining how each result aligns with user preferences and constraints. An LLM extracts intents and entities from user queries to support rule-based Cypher retrieval, while the RAG pipeline generates contextualized responses using the user query and preferences, retrieved recipes, statistical summaries, and substitution logic. The system integrates real-time updates of recipe and nutritional data, supporting up-to-date, relevant, and personalized recommendations. It is designed for language-adaptable deployment and has been developed and evaluated using Greek-language content. DietQA provides a scalable framework for transparent and adaptive dietary recommendation systems powered by conversational AI. Full article

(This article belongs to the Special Issue Natural Language Processing (NLP) and Large Language Modelling (2nd Edition))

► Show Figures

Graphical abstract

32 pages, 852 KB

Open AccessArticle

Benchmarking the Responsiveness of Open-Source Text-to-Speech Systems

by Ha Pham Thien Dinh, Rutherford Agbeshi Patamia, Ming Liu and Akansel Cosgun

Computers 2025, 14(10), 406; https://doi.org/10.3390/computers14100406 - 23 Sep 2025

Viewed by 3865

Abstract

Responsiveness—the speed at which a text-to-speech (TTS) system produces audible output—is critical for real-time voice assistants yet has received far less attention than perceptual quality metrics. Existing evaluations often touch on latency but do not establish reproducible, open-source standards that capture responsiveness as [...] Read more.

Responsiveness—the speed at which a text-to-speech (TTS) system produces audible output—is critical for real-time voice assistants yet has received far less attention than perceptual quality metrics. Existing evaluations often touch on latency but do not establish reproducible, open-source standards that capture responsiveness as a first-class dimension. This work introduces a baseline benchmark designed to fill that gap. Our framework unifies latency distribution, tail latency, and intelligibility within a transparent and dataset-diverse pipeline, enabling a fair and replicable comparison across 13 widely used open-source TTS models. By grounding evaluation in structured input sets ranging from single words to sentence-length utterances and adopting a methodology inspired by standardized inference benchmarks, we capture both typical and worst-case user experiences. Unlike prior studies that emphasize closed or proprietary systems, our focus is on establishing open, reproducible baselines rather than ranking against commercial references. The results reveal substantial variability across architectures, with some models delivering near-instant responses while others fail to meet interactive thresholds. By centering evaluation on responsiveness and reproducibility, this study provides an infrastructural foundation for benchmarking TTS systems and lays the groundwork for more comprehensive assessments that integrate both fidelity and speed. Full article

(This article belongs to the Special Issue Natural Language Processing (NLP) and Large Language Modelling (2nd Edition))

► Show Figures

Figure 1

21 pages, 356 KB

Open AccessArticle

Integrating Large Language Models with near Real-Time Web Crawling for Enhanced Job Recommendation Systems

by David Gauhl, Kevin Kakkanattu, Melbin Mukkattu and Thomas Hanne

Computers 2025, 14(9), 387; https://doi.org/10.3390/computers14090387 - 15 Sep 2025

Viewed by 1121

Abstract

This study addresses the limitations of traditional job recommendation systems that rely on static datasets, making them less responsive to dynamic job market changes. While existing job platforms address job search with an untransparent logic following their business goals, job seekers may benefit [...] Read more.

This study addresses the limitations of traditional job recommendation systems that rely on static datasets, making them less responsive to dynamic job market changes. While existing job platforms address job search with an untransparent logic following their business goals, job seekers may benefit from a solution actively and dynamically crawling and evaluating job offers from a variety of sites according to their objectives. To address this gap, a hybrid system was developed that integrates large language models (LLMs) for semantic analysis with near real-time data acquisition through web crawling. The system extracts and ranks job-specific keywords from user inputs, such as resumes, while dynamically retrieving job listings from online platforms. User evaluations indicated strong performance in keyword extraction and system usability but revealed challenges in web crawler performance, affecting recommendation accuracy. Compared with a state-of-the-art commercial tool, user tests indicate a smaller accuracy of our prototype but a higher functionality satisfaction. Test users highlighted its great potential for further development. The results highlight the benefits of combining LLMs and web crawling while emphasizing the need for improved near real-time data handling to enhance recommendation precision and user satisfaction. Full article

(This article belongs to the Special Issue Natural Language Processing (NLP) and Large Language Modelling (2nd Edition))

► Show Figures

Figure 1

18 pages, 4208 KB

Open AccessArticle

Transformer Models for Paraphrase Detection: A Comprehensive Semantic Similarity Study

by Dianeliz Ortiz Martes, Evan Gunderson, Caitlin Neuman and Nezamoddin N. Kachouie

Computers 2025, 14(9), 385; https://doi.org/10.3390/computers14090385 - 14 Sep 2025

Cited by 1 | Viewed by 1586

Abstract

Semantic similarity, the task of determining whether two sentences convey the same meaning, is central to applications such as paraphrase detection, semantic search, and question answering. Despite the widespread adoption of transformer-based models for this task, their performance is influenced by both the [...] Read more.

Semantic similarity, the task of determining whether two sentences convey the same meaning, is central to applications such as paraphrase detection, semantic search, and question answering. Despite the widespread adoption of transformer-based models for this task, their performance is influenced by both the choice of similarity measure and BERT (bert-base-nli-mean-tokens), RoBERTa (all-roberta-large-v1), and MPNet (all-mpnet-base-v2) on the Microsoft Research Paraphrase Corpus (MRPC). Sentence embeddings were compared using cosine similarity, dot product, Manhattan distance, and Euclidean distance, with thresholds optimized for accuracy, balanced accuracy, and F1-score. Results indicate a consistent advantage for MPNet, which achieved the highest accuracy (75.6%), balanced accuracy (71.0%), and F1-score (0.836) when paired with cosine similarity at an optimized threshold of 0.671. BERT and RoBERTa performed competitively but exhibited greater sensitivity to the choice of Similarity metric, with BERT notably underperforming when using cosine similarity compared to Manhattan or Euclidean distance. Optimal thresholds varied widely (0.334–0.867), underscoring the difficulty of establishing a single, generalizable cut-off for paraphrase classification. These findings highlight the value of fine-tuning of both Similarity metrics and thresholds alongside model selection, offering practical guidance for designing high-accuracy semantic similarity systems in real-world NLP applications. Full article

(This article belongs to the Special Issue Natural Language Processing (NLP) and Large Language Modelling (2nd Edition))

► Show Figures

Figure 1

Review

Jump to: Research

32 pages, 1254 KB

Open AccessReview

Arabic Natural Language Processing (NLP): A Comprehensive Review of Challenges, Techniques, and Emerging Trends

by Abdulaziz M. Alayba

Computers 2025, 14(11), 497; https://doi.org/10.3390/computers14110497 - 15 Nov 2025

Viewed by 2412

Abstract

Arabic natural language processing (NLP) has garnered significant attention in recent years due to the growing demand for automated text and Arabic-based intelligent systems, in addition to digital transformation in the Arab world. However, the unique linguistic characteristics of Arabic, including its rich [...] Read more.

Arabic natural language processing (NLP) has garnered significant attention in recent years due to the growing demand for automated text and Arabic-based intelligent systems, in addition to digital transformation in the Arab world. However, the unique linguistic characteristics of Arabic, including its rich morphology, diverse dialects, and complex syntax, pose significant challenges to NLP researchers. This paper provides a comprehensive review of the main linguistic challenges inherent in Arabic NLP, such as morphological complexity, diacritics and orthography issues, ambiguity, and dataset limitations. Furthermore, it surveys the major computational techniques employed in tokenisation and normalisation, named entity recognition, part-of-speech tagging, sentiment analysis, text classification, summarisation, question answering, and machine translation. In addition, it discusses the rapid rise of large language models and their transformative impact on Arabic NLP. Full article

(This article belongs to the Special Issue Natural Language Processing (NLP) and Large Language Modelling (2nd Edition))

► Show Figures

Figure 1

Journal Menu

Journal Browser

Natural Language Processing (NLP) and Large Language Modelling (2nd Edition)

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Related Special Issue

Published Papers (8 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI