Curated for content, computing, and digital experience professionals

Category: Semantic technologies (Page 1 of 68)

Our coverage of semantic technologies goes back to the early 90s when search engines focused on searching structured data in databases were looking to provide support for searching unstructured or semi-structured data. This early Gilbane Report, Document Query Languages – Why is it so Hard to Ask a Simple Question?, analyses the challenge back then.

Semantic technology is a broad topic that includes all natural language processing, as well as the semantic web, linked data processing, and knowledge graphs.

Google Translate learns 24 new languages

From the Google Products Blog…

… today we’ve added 24 languages to Translate, now supporting a total of 133 used around the globe.

Over 300 million people speak these newly added languages — like Mizo, used by around 800,000 people in the far northeast of India, and Lingala, used by over 45 million people across Central Africa. As part of this update, Indigenous languages of the Americas (Quechua, Guarani and Aymara) and an English dialect (Sierra Leonean Krio) have also been added to Translate for the first time.

This is also a technical milestone for Google Translate. These are the first languages we’ve added using Zero-Shot Machine Translation, where a machine learning model only sees monolingual text — meaning, it learns to translate into another language without ever seeing an example. While this technology is impressive, it isn’t perfect. And we’ll keep improving these models to deliver the same experience you’re used to with a Spanish or German translation, for example. If you want to dig into the technical details, check out our Google AI blog post and research paper. updates AI-based natural language processing platform announced the new release of its platform combining symbolic, human-like comprehension and machine learning to turn language into data, analyze and understand complex documents, accelerate intelligent process automation and improve decision making. By extending core features and adding unique capabilities, such as out of the box knowledge models and connectors, the new release increases flexibility, simplifies integration and optimizes data pipelines to augment efficiency across every process that involves natural language (NL).

Specifically designed for natural language AI, the platform leverages the combination of different AI techniques (machine learning and rule-based symbolic comprehension) with a simple and powerful authoring environment to support the full natural language processing workflow. It is based on the principle that no single natural language AI technique is a fit for every project. The new release includes:

  • ‘Smarter from the start’ knowledge models deliver NL applications to production faster with higher levels of business accuracy
  • Simplified deployment processes across multiple environments, including Azure
  • Easier integration, out of the box connectors
  • Enhanced natural language operations: provides the ability to include custom Python and Java scripts or third-party services for pre- or post-processing activities in NL workflow orchestrations.

AppTek launches new metadata-informed neural machine translation system

‍AppTek, a provider of Artificial Intelligence (AI) and Machine Learning (ML) for Automatic Speech Recognition (ASR), Neural Machine Translation (NMT), Natural Language Processing / Understanding (NLP/U) and Text-to-Speech (TTS) technologies, announced the release of its new neural machine translation system that incorporates metadata as inputs used to customize the MT output and empower localization professionals with more accurate user-influenced machine translations. Additionally, the company expanded its core machine translation platform to support hundreds of language and dialect pairs.

Traditionally, enterprises would need to train, deploy and maintain multiple MT systems to account for translation tasks that differ in aspects such as language, dialect, domain, topic, and more, at the risk of high deployment costs and overfitting models.

With AppTek’s new metadata informed NMT platform, enterprise customers can now access a single NMT system with multi-domain, multi-genre, multi-dialect content which increases the quality and adaptability of the system. By feeding additional metadata into the system, they gain more control of the MT output and can enable translators to simply “flip the switch” to the desired customized translation through relevant functionality in the user interface of the editing tools professionals work with.

Access Innovations announces Video/Audio to Text to Tagging solution for video transcript search

Access Innovations, Inc. announced Video/Audio to Text to Tagging (VATT), a solution that translates audio files to time stamped text transcripts for indexing, classifying, and enriching by Data Harmony Hub. Originally developed to improve search precision on training videos for a large chemical manufacturer, the new tagging capabilities can be used on any video or audio content from lectures, demonstrations, conferences, and more. Once metadata tagging is completed by Data Harmony Hub, a “point in time” search allows for users to find the precise time within the video/audio where the speaker or narrator discusses a specific topic, without wasting time browsing and scrolling through the entire video to find the information they need.

Organizations are generating video content and placing it on YouTube and other video aggregation service platforms. If transcripts are not available and searchable, the viewer is disappointed when they attempt to search a library of videos. In most cases, search is only available on the video title, the speaker or performer name, and possibly the date. With the video/audio to text to tagging solution, viewers enjoy a more robust search experience, reduce noise within the search results, and pinpoint topics and concepts of interest.

Semantic Web Company and WAND Inc. announce partnership

WAND, Inc. announced a new partnership with Semantic Web Company. This partnership will blend the offerings of Semantic Web’s taxonomy management system with WAND’s taxonomies to accelerate client time to delivery. PoolParty opens up the use of WAND’s domain taxonomies to jump-start enterprise search, text analytics, business intelligence, artificial intelligence, knowledge graphs, and sentiment analysis. Based on a solid taxonomy, customers can invest more time and effort in customizing and thus fine-tuning their Knowledge Graph applications. The benefits of this new partnership include:

  • Informing A.I. Engines with a curated knowledge model
  • Speeding up time to delivery for projects
  • An extensibility to all domains of knowledge
  • Bundled pricing of WAND Taxonomies and PoolParty license


Elastic releases Elastic 8.0

Elastic announced the general availability of Elastic 8.0 with enhancements across the Elastic Search Platform and its Enterprise Search, Observability, and Security solutions. Updates include native vector search, native support for modern natural language processing models, simplified data onboarding, and a streamlined security experience.

Native support for natural language processing (NLP) enables the use of custom or third-party PyTorch machine learning models directly in Elasticsearch. The addition of native NLP support with vector search enables users to perform inference within Elasticsearch, resulting in faster and more relevant search results. Customers can now leverage enhanced vector search capabilities, including native support for approximate nearest neighbor (ANN) search, to quickly perform queries on enormous data sets such as documents, images, and audio files.

Elastic native vector search extends technology commonly associated with searching for image and text content into the world of business data. Organizations can use vector search with NLP support to deliver faster, more relevant customer support information, improve shopping experiences, and enhance search accessibility by providing unique audio and visual search results. A simplified Elastic Cloud on AWS onboarding experience includes new integrations to speed data ingestion, including the new Elastic Serverless Forwarder.

Access Innovations launches Data Harmony Hub for automated content classification and semantic metadata enrichment

Access Innovations, Inc. announced the launch of Data Harmony Hub, a cloud-based platform that provides fully automated content tagging using expertly curated taxonomies. Users can easily and quickly select from a variety of existing taxonomies that are continuously maintained and updated. Data Harmony Hub is a managed service allowing organizations that need their content to be tagged to improve search for their users, to provide better insight into their digital assets, to identify new revenue streams, and to greatly reduce risk and compliance issues.

The Data Harmony Hub is the result of working with Access Innovations’ clients over many years to understand their goal to integrate a tagging and semantic enrichment process into their workflow. The low-code integration allows organizations to easily connect their content management system or document store to Data Harmony Hub. Once integrated, the managed service works behind the scenes 24/7 to improve the findability and discoverability of content.

Franz’s Gruff 8.1 brings visual knowledge graphs to web applications

Franz Inc., supplier of graph database technology for entity-event knowledge graph solutions, announced Gruff 8.1, a knowledge graph visualization software tool that can be embedded in any web page or web application. Users can now visually build queries and visualize connections between enterprise data directly within a web page or web application, enabling a simple and seamless knowledge discovery experience.

Gruff, available as a browser-based application or pre-integrated into AllegroGraph, is a no-code visual query application that enables users to create visual Knowledge Graphs that display data relationships in views driven by the user. Gruff’s visual query builder empowers both novice and expert users to create simple to complex queries without writing code. The ‘Time Machine’ function within Gruff gives users the capability to explore temporal context and connections within data. Visualizations can be customized to fit a specific user experience, data relationships, or business requirements.

Special dialogs appear in Gruff 8.1 when saving or loading a SPARQL query, graphical query, or layout. The dialog shows descriptive information about each file and allows the user to filter the list of choices in various ways to make it easier to locate the desired file.

« Older posts

© 2022 The Gilbane Advisor

Theme by Anders NorenUp ↑