Curated for content, computing, and digital experience professionals

Month: May 2023 (Page 2 of 3)

Gilbane Advisor 5-17-23 — LLMs KGs & DBs, chatbot UIs

This week we feature articles from Dean Allemang, and Tim Neusesser & Evan Sunwall.

Additional reading comes from Amelia Wattenburger, Google I/O presenters, and Allen Institute staff.

News comes from Tridion, Adobe & Google, MindsDB & Nixtla, and Algolia.

All previous issues are available at

Opinion / Analysis

AI’s Woolf at the door — LLMs and knowledge graphs

The combination of Large Language Models with other sources of data and knowledge has enormous potential for new, and more powerful, applications across domains. Most of the examples we’ve looked at in the last few weeks involve knowledge graphs and LLMs, which seem like particularly promising partners. Dean Allemang reports from last week’s Knowledge Graph Conference that there is a lot of enthusiasm for such a marriage. But Allemang wants more evidence that knowledge graphs are in fact a better match for LLMs than other types of databases. His article is a good place to start for anyone who has the same question. (8 min)

Error-message guidelines

Who among us hasn’t been occasionally baffled by error messages that aren’t the least bit helpful? This is one of the most frustrating user experience failures. Tim Neusesser and Evan Sunwall describe what designers should watch out for, and review good and bad error-message examples (including one they like from ChatGPT – see the first item in the list just below for more on chatbot UIs.) (7 min)

More Reading

All Gilbane Advisor issues

Content technology news

Tridion unites web content, structured content and headless delivery

Includes Tridion Docs 15, Tridion Sites 10, updated Tridion Dynamic Experience Delivery, and embedded Fonto for structured content authoring.

Adobe and Google integrating Firefly and Bard

Adobe will use the Content Authenticity Initiative’s (CAI) open-source Content Credentials technology for transparency to images generated.

MindsDB and Nixtla enhance time-series forecasting

The integration allows developers using MindsDB to build AI forecasting capabilities and anomaly detection in the database without extensive code. ■‍

Algolia launches AI-powered Algolia NeuralSearch

NeuralSearch uses Large Language Models (LLM) and Algolia’s Neural Hashing for hyper-scale, and constantly learns from user interactions.

All content technology news

The Gilbane Advisor is authored by Frank Gilbane and is ad-free, cost-free, and curated for content, computing, web, data, and digital experience technology and information professionals. We publish recommended articles and content technology news weekly. We do not sell or share personal data.

Subscribe | View online | Editorial policy | Privacy policy | Contact launches AI platform for Life Sciences announced availability of the Platform for Life Sciences. With the Platform for Life Sciences, teams can access advanced natural language understanding capabilities, learning methodologies, 3rd-party large language models like BioBert and Bio-GPT as well as customizable pre-built knowledge models to build custom solutions.

Through a hybrid AI approach combining natural language tools, enterprise language models and machine learning, the Platform for Life Sciences shifts the way unstructured medical and scientific data is monitored, understood, analyzed and collated. Teams can access knowledge and insights trapped in medical articles, reports, press releases, clinical research, customer/patient interactions, consent forms, etc. as well as up-to-date knowledge available based on standards like MeSH, UMLS Conditions & Interventions and IUPAR. Pharmaceutical and Life Sciences teams can:

  • Confirm scientific claims against trusted public and private knowledge sources;
  • Extract connections between biomedical entities in literature for in-depth causality analysis to support researchers; 
  • Monitor clinical trials and social media sources filtered by any combination of indication, drug, mechanism of action, sponsor, or geography to gain insight for clinical trials; 
  • Accelerate the quality control process of clinical and preclinical reports analysis using sensitive and proprietary data sources prior to their submission to regulatory bodies.

Ontotext releases Target Discovery

Ontotext announced the release of Target Discovery, an AI-powered platform that speeds the process of discovering new safe and efficient drug candidates. Target Discovery combines knowledge from public and proprietary data, AI-derived data from scientific publications, patents and clinical trials. It also features analytics for target identification and selection that medical or scientific experts without technical skills. Knowledge graph technology can lower the cost and shorten the time for semantic data integration. It also brings in a new level of insights on top of highly connected data and provides normalized quality data for supporting AI analysis. Benefits include:

  • Target Discovery stays up-to-date with the newest discoveries by automatically extracting knowledge from more than 80 million documents, including patents and clinical trials.
  • Target Discovery combines all required data, whether public or proprietary, AI-derived or structured in one place. Information is updated regularly and includes a selections from AlphaFold, Open Targets, EMBL.
  • One can quickly gain an overview of a disease or target with customizable visual analytics and dashboards over any type of data and source.
  • Hidden relationships can be easily uncovered in a network of over 5 billion facts with advanced graph algorithms.
  • Transparent insight provenance and evidence.

Tridion unites web content, structured content and headless delivery

RWS, a provider of technology-enabled language, content and intellectual property services, announced the launch of its next major release of Tridion, RWS’s intelligent multilingual content management system. The platform combines web content, structured content and headless delivery in a single solution, for organizations with heavy content demands.

The new platform helps clients to better orchestrate the creation, management, translation and delivery of content to any digital touchpoint across the customer journey. It means that customers, employees and partners can expect a consistent experience, in their own language, on any device or channel. Includes: 

  • Headless Delivery – fine-grained access to content components and semantic modeling of headless content.
  • Content Discovery – now also natively provides additional content services such as intelligent content recommendations.
  • Content Security – further modernized features for access management, authentication and audit trails.
  • User Experience and Workflow –simplified and aligned with daily user tasks with a direct impact on productivity for both web content and long-form structured content.
  • Content Globalization – further streamlined translation workflows integrated with RWS’s translation technology. 

Tridion Docs 15, Tridion Sites 10, an updated version of Tridion Dynamic Experience Delivery (DXD) and new embedded version of Fonto for structured content authoring, will be available in July 2023.

Sinequa enhances platform for scientific search and clinical trial data

AI-powered search provider Sinequa has announced domain-specific enhancements to its intelligent search platform for Scientific Search and Clinical Trial Data. Its search platform now utilizes new Neural Search and ChatGPT capabilities for faster, more effective discovery and decisions in drug development and clinical research. Sinequa will present these capabilities at the 2023 Bio-IT World Conference, May 16-18, at the Boston Convention and Exhibition Center, during conference sessions and at booth #803 in Auditorium Hall C. 

Combining the capabilities of Sinequa Neural Search – multiple deep learning and large language models for natural language understanding (NLU) – with the latest ChatGPT models through Azure OpenAI Service, Sinequa enables accurate, fast, traceable semantic search, insight generation, and summarization. Users can query and converse with a secure corpus of data, including proprietary life science systems, enterprise collaboration systems, and external data sources, to answer complex and nuanced questions. Comprehensive search results with high relevance and the ability to generate concise summaries enhance R&D intelligence, optimize clinical trials, and streamline regulatory workflows.

Adobe and Google integrating Firefly and Bard

Adobe and Google are partnering to bring Firefly to Bard, Google’s experimental conversational AI service, with the ability to continue the creative journey further in Adobe Express. With the new Bard by Google integration, users at all skill levels will be able to describe their vision to Bard in their own words to create Firefly generated images directly in Bard and then modify and use them to create designs via Express.

Because Firefly has the CAI’s Content Credentials on by default, every image created in Bard using Firefly will have transparency built in. The CAI’s Content Credentials are a free, open-source tool that serve as a digital “nutrition label.” Content Credentials can show information such as name, date, the tools used to create an image and any edits made to that image. They remain associated with content wherever it is used, published or stored, enabling proper attribution and helping consumers make informed decisions about digital content.

Firefly’s first model is trained on Adobe Stock images, openly licensed content and public domain content where copyright has expired. Enterprise businesses will be able to train Firefly with their own creative collateral in order to generate content in the company’s brand language.

MindsDB and Nixtla enhance time-series forecasting

MindsDB, an open-source applied machine learning platform, announced full integration with Nixtla, an open-source ecosystem that offers time-series forecasting.

Time-series forecasting refers to making scientific predictions based on historical, time-stamped data. It allows data scientists to employ models to predict a future value or classification at a particular point in time, such as forecasting power demand, call volumes, inventory requirements, or supply and demand.

Nixtla offers libraries specifically for time-series forecasting. One of the libraries, StatsForecast, which provides statistical and econometric models, will now function seamlessly within the MindsDB ecosystem. This integration will allow developers using MindsDB to build AI-powered forecasting capabilities and anomaly detection solutions in the database without writing extensive code. MindsDB turns a team of 1,000 developers into 1,000 AI developers with little to no training.

The Nixtla integration includes accurate model implementations, probabilistic forecasting and confidence intervals, support for exogenous variables and static covariates, anomaly detection and time series forecasting. Nixtla’s StatsForecast is optimized for high performance and scalability and uses classical methods, such as ARIMA, rather than deep learning models. This platform means models can be trained quickly and generalized well, making short-time series forecasting easier for developers. ■‍

TransPerfect launches GlobalLink Connect app for Contentstack’s DXP

TransPerfect, a provider of language and technology solutions for global business, announced that its new GlobalLink Connect app is now available on the Contentstack Marketplace, part of Contentstack’s Composable Digital Experience Platform (DXP). Contentstack Marketplace’s apps allow users to extend the capability of Contentstack’s content management solution and customize its functionalities by easily integrating third-party platforms. The GlobalLink Connect for Contentstack app enables customers to:

  1. Select single or multiple entries for translation using the Translation Wizard dashboard
  2. Track the status of any project in real time with the new entry sidebar widget
  3. Manage and control content translation projects with the new configuration screen
  4. Configure translation for any content type using the new field configuration widget

GlobalLink is TransPerfect’s modular suite of tools specifically designed to manage the complex demands of creating, deploying, and maintaining multilingual content, drastically reducing the time and effort required throughout the localization process.

« Older posts Newer posts »

© 2024 The Gilbane Advisor

Theme by Anders NorenUp ↑