Announcing the general availability of OCI Language 4.0

We're thrilled to announce the general availability of Oracle Cloud Infrastructure (OCI) Language 4.0 in all OCI regions. OCI Language 4.0 introduces three new capabilities as part of Oracle's commitment to provide high quality, affordable text analytics services for our customers. OCI Language is a cloud-based AI service that performs sophisticated text analysis at scale. AI Language services are helpful to gain insights from unstructured data and make important business decisions.

Features of OCI Language 4.0

OCI Language 4.0 includes the following features and benefits:

• Health natural language processing (NLP): Provides AI models to extract entities from electronic health records (EHRs), progress notes, clinical trial documents, and so on. Healthcare NLP is a suite that includes the following models:
  • Health named entity recognition (Health NER): Identifies key entities from text including identifying medical conditions, medications, dosages, symptoms, test results, treatments, and procedures.
  • Relationship extraction: Identify relationships between different medical entities. For example, it extracts the relationship between the medication and dosage.
  • Assertion detection: Identifies contextual modifiers to the extracted entities, such as the status, subject, time, and certainty. For example, certainty indicates whether the medical concept is certain, possible, hypothetical, conditional, or uncertain.
  • Medical entity linking: Link the extracted entities with codes from the biomedical vocabularies: SNOMED-CT and ICD-10. For example acute stress reaction is linked to F43.0 code (ICD-10), and detection of SARS-CoV-2is linked to 871562009 code (SNOMED-CT).

• Protected health information (PHI) identification and deidentification: The PHI service extends current PII service to detect PHI entities and provides the option to deidentify and anonymize identified entities from output.

• Multilingual pretrained models: OCI Language's pretrained models now support processing multilingual text. The pretrained models provide the highest accuracy for analyzing unstructured text. English and Spanish are already supported for sentiment analysis, key-phrase extraction, and NER. This release introduces support of Arabic, French, German, and Italian.

Conclusion

OCI Language 4.0 introduces advanced features, including PHI support, specialized health models, and multilingual language model support. These enhancements empower users with seamless language understanding, efficient processing of health records, scalable text analytics, and superior capabilities for extracting valuable insights from diverse textual data sources. With these powerful new capabilities, OCI Language 4.0 represents a significant leap forward in delivering comprehensive, enterprise-grade text analytics to our customers across all OCI regions.

Are you ready to embark on this exciting journey? Dive into the world of Oracle Cloud Infrastructure Language with the following resources:

• Language service LiveLab
• OCI Language product page
• OCI Language documentation
• API reference
• GitHub samples