Natural Language Engineering

Papers
(The median citation count of Natural Language Engineering is 3. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2022-08-01 to 2026-08-01.)
ArticleCitations
Emerging trends: Smooth-talking machines47
From unified phrase representation to bilingual phrase alignment in an unsupervised manner38
NLE volume 28 issue 6 Cover and Back matter26
Neural Arabic singular-to-plural conversion using a pretrained Character-BERT and a fused transformer25
Recognition of visual scene elements from a story text in Persian natural language23
RoLEX: The development of an extended Romanian lexical dataset and its evaluation at predicting concurrent lexical information22
An unsupervised perplexity-based method for boilerplate removal19
Linguistically aware evaluation of coreference resolution from the perspective of higher-level applications16
Killing me softly: Creative and cognitive aspects of implicitness in abusive language online15
Towards diverse and contextually anchored paraphrase modeling: A dataset and baselines for Finnish14
Focusing on potential named entities during active label acquisition13
Emojis as anchors to detect Arabic offensive language and hate speech11
Anisotropic span embeddings and the negative impact of higher-order inference for coreference resolution: An empirical analysis10
Data-to-text generation using conditional generative adversarial with enhanced transformer9
NLP startup funding in 20229
The problem of varying annotations to identify abusive language in social media content8
Perceptional and actional enrichment for metaphor detection with sensorimotor norms8
A comparison of latent semantic analysis and correspondence analysis of document-term matrices8
An end-to-end neural framework using coarse-to-fine-grained attention for overlapping relational triple extraction7
SSL-GAN-RoBERTa: A robust semi-supervised model for detecting Anti-Asian COVID-19 hate speech on social media6
Leveraging machine translation for cross-lingual fine-grained cyberbullying classification amongst pre-adolescents6
Creating a large-scale diachronic corpus resource: Automated parsing in the Greek papyri (and beyond)6
How you describe procurement calls matters: Predicting outcome of public procurement using call descriptions6
Argumentation models and their use in corpus annotation: Practice, prospects, and challenges5
Korean named entity recognition based on language-specific features – CORRIGENDUM5
Preface: Special issue on NLP approaches to offensive content online5
Improved conversational recommender system based on dialog context5
Ad astra or astray: Exploring linguistic knowledge of multilingual BERT through NLI task – CORRIGENDUM5
Soap ’n’ AI5
Navigating the text generation revolution: Traditional data-to-text NLG companies and the rise of ChatGPT4
Recommending tasks based on search queries and missions4
Obituary: Yorick Wilks4
Editorial Note4
Quinductor: A multilingual data-driven method for generating reading-comprehension questions using Universal Dependencies4
Assessment of the E3C corpus for the recognition of disorders in clinical texts4
Emerging trends: Risks 3.0 and proliferation of spyware to 50,000 cell phones3
Automated annotation of parallel bible corpora with cross-lingual semantic concordance3
Start-up activity in the LLM ecosystem3
Actionable conversational quality indicators for improving task-oriented dialog systems3
Improving aspect-based neural sentiment classification with lexicon enhancement, attention regularization and sentiment induction3
Parameter-efficient feature-based transfer for paraphrase identification3
NLE volume 28 issue 5 Cover and Back matter3
Towards universal methods for fake news detection3
What should be encoded by position embedding for neural network language models?3
Emerging trends: Deep nets thrive on scale3
Describe the house and I will tell you the price: House price prediction with textual description data3
SEN: A subword-based ensemble network for Chinese historical entity extraction3
0.056636095046997