Skip to content
GCC AI Research

Search

Results for "tagging"

An Empirical Study of Pre-trained Transformers for Arabic Information Extraction

arXiv ·

This paper introduces GigaBERT, a customized bilingual BERT model pre-trained for Arabic NLP and English-to-Arabic zero-shot transfer learning. The study evaluates GigaBERT's performance on four information extraction tasks: named entity recognition, part-of-speech tagging, argument role labeling, and relation extraction. Results show that GigaBERT outperforms mBERT, XLM-RoBERTa, and AraBERT in both supervised and zero-shot transfer settings. Why it matters: GigaBERT advances Arabic NLP by providing a high-performing, publicly available model tailored for the complexities of the Arabic language and cross-lingual applications.

Fanar 2.0 a major leap in Arabic AI technology - The Peninsula Qatar

QCRI ·

Qatar Computing Research Institute (QCRI) has released Fanar 2.0, a new version of its open-source Arabic language processing toolkit. Fanar 2.0 includes improved models for named entity recognition, part-of-speech tagging, and dependency parsing. The toolkit is designed to support researchers and developers working on Arabic NLP applications. Why it matters: This release enhances the accessibility of advanced Arabic NLP tools, crucial for developing AI solutions tailored to the Arabic-speaking world.

KAUST developed fish wearable technology wins CES Innovation Award

KAUST ·

KAUST's Bluefin, a fish wearable technology developed by Professor Muhammad Mustafa Hussain, won the CES Innovation Award. The device measures water temperature, pressure, depth, and pH levels, functioning for a year at a depth of 2km while weighing only 2.4 grams. Bluefin will be available to scuba divers, naval forces, and fisheries for marine life tagging. Why it matters: This award recognizes KAUST's contributions to marine research technology and positions the university as a global leader in applying advanced engineering to ecological monitoring.

The internet of sea things

KAUST ·

KAUST researchers developed a hybrid wireless communication system for non-invasive monitoring of marine animals, consisting of a lightweight, flexible, Bluetooth-enabled tag that stores sensor data underwater. The tag syncs data to floating receivers when the animal surfaces, which then relays the data via GSM or drones. The system is a collaboration between the Red Sea Research Center and KAUST's electrical engineering department. Why it matters: This technology provides researchers with detailed, near real-time data about marine animals, overcoming the limitations of invasive and impractical traditional tagging methods.

Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging

arXiv ·

This paper explores language-independent alternatives to morphological segmentation for Arabic NLP using data-driven sub-word units, characters as a unit of learning, and word embeddings learned using a character CNN. The study evaluates these methods on machine translation and POS tagging tasks. Results show these methods achieve performance close to or surpassing state-of-the-art approaches. Why it matters: By offering simpler, more adaptable segmentation techniques, this research can help improve Arabic NLP applications across diverse domains and dialects.

Tags reveal Chilean devil rays are among ocean's deepest divers

KAUST ·

KAUST researchers and international collaborators tagged 15 Chilean devil rays in the Atlantic, revealing unexpected deep-diving behavior. The tags recorded dives reaching almost 2,000 meters at speeds of 6 meters per second and temperatures below 4 degrees Celsius. The rays exhibited two distinct diving patterns, including long periods at 1,000 meters and stepwise returns to the surface, possibly for thermoregulation. Why it matters: This research challenges previous assumptions about devil ray behavior and highlights KAUST's contribution to marine biology and understanding of ocean ecosystems.

An Accurate Arabic Root-Based Lemmatizer for Information Retrieval Purposes

arXiv ·

This paper introduces a new non-statistical Arabic lemmatizer algorithm designed for information retrieval systems. The lemmatizer leverages Arabic language knowledge resources to generate accurate lemma forms and relevant features. The algorithm achieves a maximum accuracy of 94.8% and 89.15% on first seen documents, outperforming the Stanford Arabic model's 76.7% on the same dataset. Why it matters: Accurate Arabic lemmatization is crucial for improving the performance of Arabic information retrieval systems, which can enhance access to Arabic language content.