OOIR: Observatory of International Research

Papers

(The TQCC of Natural Language Engineering is 2. 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 2020-05-01 to 2024-05-01.)

Article	Citations
GPT-3: What’s it good for?	184
A Survey on Machine Reading Comprehension Systems	19
Comparison of rule-based and neural network models for negation detection in radiology reports	17
Emerging trends: A gentle introduction to fine-tuning	16
TNT-KID: Transformer-based neural tagger for keyword identification	16
The automated writing assistance landscape in 2021	16
Natural language generation: The commercial state of the art in 2020	15
Recent advances in processing negation	15
Neural machine translation of low-resource languages using SMT phrase pair injection	15
Improving sentiment analysis with multi-task learning of negation	14
Automatic classification of participant roles in cyberbullying: Can we detect victims, bullies, and bystanders in social media text?	12
Emerging Trends: SOTA-Chasing	12
Automatic question generation based on sentence structure analysis using machine learning approach	12
Spoken Arabic dialect recognition using X-vectors	10
Supervised learning for the detection of negation and of its scope in French and Brazilian Portuguese biomedical corpora	10
Comparison of text preprocessing methods	9
Universal Lemmatizer: A sequence-to-sequence model for lemmatizing Universal Dependencies treebanks	9
Natural language processing for similar languages, varieties, and dialects: A survey	9
Emojis as anchors to detect Arabic offensive language and hate speech	9
Named-entity recognition in Turkish legal texts	8
Computational generation of slogans	7
Negation detection for sentiment analysis: A case study in Spanish	7
UNLT: Urdu Natural Language Toolkit	7
SwitchNet: Learning to switch for word-level language identification in code-mixed social media text	7
Enhancement of Twitter event detection using news streams	7

Improving short text classification with augmented data using GPT-3	7
Turkish abstractive text summarization using pretrained sequence-to-sequence models	6
Focus of negation: Its identification in Spanish	6
Emerging trends: Deep nets for poets	6
Gender bias in legal corpora and debiasing it	6
In-depth analysis of the impact of OCR errors on named entity recognition and linking	6
Sentence encoding for Dialogue Act classification	5
Automatic generation of lexica for sentiment polarity shifters	5
Automated hate speech detection and span extraction in underground hacking and extremist forums	4
Compression versus traditional machine learning classifiers to detect code-switching in varieties and dialects: Arabic as a case study	4
The voice synthesis business: 2022 update	4
Deception detection in text and its relation to the cultural dimension of individualism/collectivism	4
Improving speech emotion recognition based on acoustic words emotion dictionary	4
Emerging trends: Unfair, biased, addictive, dangerous, deadly, and insanely profitable	3
A clustering framework for lexical normalization of Roman Urdu	3
SSL-GAN-RoBERTa: A robust semi-supervised model for detecting Anti-Asian COVID-19 hate speech on social media	3
Authorship attribution using author profiling classifiers	3
A survey of the extraction and applications of causal relations	3
A note on constituent parsing for Korean	3
Natural Language Processing for Corpus Linguistics by Jonathan Dunn. Cambridge: Cambridge University Press, 2022. ISBN 9781009070447 (PB), ISBN 9781009070447 (OC), vi+88 pages.	3
An empirical study of cyclical learning rate on neural machine translation	3
Improved feature decay algorithms for statistical machine translation	3
RoLEX: The development of an extended Romanian lexical dataset and its evaluation at predicting concurrent lexical information	3
Imparting interpretability to word embeddings while preserving semantic structure	2
Towards syntax-aware token embeddings	2
Neural Machine Translation 2020, by Philipp Koehn, Cambridge, Cambridge University Press, ISBN 978-1-108-49732-9, pages 393.	2
Benchmarks and goals	2
Annotating argumentative structure in English-as-a-Foreign-Language learner essays	2
Automated evaluation of the quality of ideas in compositions based on concept maps	2
Joint learning of morphology and syntax with cross-level contextual information flow	2
Linguistic knowledge-based vocabularies for Neural Machine Translation	2
Creation of annotated country-level dialectal Arabic resources: An unsupervised approach	2
Incorporating word embeddings in unsupervised morphological segmentation	2
Lexicon or grammar? Using memory-based learning to investigate the syntactic relationship between Belgian and Netherlandic Dutch	2
Gamified crowdsourcing for idiom corpora construction	2
$NLP: How to spend a billion dollars	2
Enhancing deep neural networks with morphological information	2
Leveraging machine translation for cross-lingual fine-grained cyberbullying classification amongst pre-adolescents	2
Killing me softly: Creative and cognitive aspects of implicitness in abusive language online	2
Towards improving coherence and diversity of slogan generation	2
Topical language generation using transformers	2