As summer slowly faded into autumn, the LangTec team set out on a team-building adventure that embraced both Hamburg’s rich history and its modern transformations. The weather held out just long enough for us to complete our climb and experience one of Hamburg’s most unique landmarks, the St. Pauli Bunker.  The bunker, which has been recently transformed into the “Green Bunker,” offers a rare combination of history, architecture, and nature. Open to the public since July, its rooftop garden—the highest in Hamburg—features 23,000 trees, shrubs, and plants spread over five pyramid-like floors. Despite the gray skies, the panoramic views of the Elbphilharmonie, Michel, and the harbour were as stunning as promised.

After our hike, we settled into the bunker’s café Constant Grind for a cozy break, where we played the board game “Concept.”  The game, where you must guess words through the association of icons, seemed almost designed for a group of programmers and linguists like ours. We deconstructed meanings, toyed with symbols, and uncovered connections.

Finally, we ended the evening with a 3-course mystery dinner at La Sala, the restaurant inside the bunker. The meal was a surprise, and each course offered something new and delicious. It was the perfect way to wrap up an eventful, drizzly, yet memorable day.

It was with these words that our client entitled the e-mail in which they informed us about having won this contract. After months of intense alignments we are delighted to have been awarded the contract for the development of two new document parsers in the shipping and sea freight sector. Specifically, we will provide a customised instance of DocumentReader and operate it for our client. DocumentReader is LangTec’s custom solution for the high-precision extraction of business-relevant information from documents in any type of format. As a cloud-based service, DocumentReader integrates seamlessly into any digital process.

Our customer is a world-renowned, publicly listed company nd one of the top logistics companies worldwide. We are super-happy about this cooperation and a also a little proud of the fact that the DocumentReader’s amazing extraction precision has convinced our customer to partner with LangTec for this exciting project. Watch this space for more updates.

LangTec has taken over a consultancy for the central IT services management of a leading multinational insurance group. The purpose is to introduce automation and artificial intelligence (AI) for improved efficiency in ITIL-compliant business processes. The scope comprises both the transfer of knowledge about AI generally and application to specific recurring use cases as well as medium-term planning of further development.

The mandate specifically targets process optimization via AI in change management, incident response, licence administration and vulnerability management. All these business cases are currently implemented in a standard ERP platform with extensive customizations and are subject to considerable regulatory constraints. Although central configuration management database ultimately contains all relevant information about persons, groups, devices, licences, tasks etc., these are often not available in the necessary context of the daily tasks.

LangTec will tackle challenges such as: automatic evaluation of incoming Change Items (Is the risk evaluation meaningful and accurate? Are all affected work groups linked?) or Incident Tickets (Are all relevant descriptions present?), data visualisation (dashboards displaying the status of incidents or aupporting auditing by management) or aggregated evaluation of the current status (Can an imminent major outage be recognized early?).

We look forward to the next months of intensive and engaging cooperation!

LangTec is excited to announce its latest collaboration in data engineering with a globally leading chemical and consumer goods company headquartered in Düsseldorf, Germany. The focus of this project is on enhancing our client’s data infrastructure. As part of the project, LangTec will play an integral role in the development of a comprehensive data catalogue and data mesh, ensuring the reliability and governance of data sources across various departments within the organisation.

The project involves the provision of expert guidance on data architecture and connections, implementing and constructing efficient data pipelines, and performing essential data transformations to meet the diverse business needs. This comprehensive approach enables our client to harness the full potential of their data assets, driving informed decision-making and operational efficiency.

This client project underscores LangTec’s commitment to delivering cutting-edge data solutions, fostering innovation, and making a contribution to the empowerment of large-scale organisations to optimise their data assets and processes.

This article examines the performance of large language models (LLMs) like ChatGPT4-Turbo and ChatGPT4-Omni for information extraction tasks, comparing them with LangTec’s specialized E-MailParser. Our analysis reveals significant limitations of LLMs in this domain.

Benchmarking Accuracy Scores

To benchmark the accuracy of ChatGPT4-Turbo, ChatGPT4-Omni, and LangTec’s E-MailParser, we conducted a comprehensive evaluation using 20 documents across four extraction tasks:

• Q88: Vetting Questionnaires for Tanker Information
• Timesheet: Tanker Loading/Unloading Statements of Fact
• Ship: Requests for Commercial Cargo Shipping
• Cargo: Commercial Cargo Vessel Position Lists

From each of these documents we extracted about 20 target data points. For the evaluation,These documents had predefined ground truth labels, indicating the expected target values for each field. By comparing the extracted values to these ground truth labels, we were able to calculate accuracy scores for each model.

Benchmark Results: LLMs vs. LangTec’s E-MailParser

Both ChatGPT4-Turbo and ChatGPT4-Omni show some level of accuracy in information extraction tasks, achieving overall scores of 56 % and 49 % respectively. Notably, the newer model ChatGPT4-Omni performs worse on this task for most document types than its predecessor ChatGPT4-Turbo. Another important observation was that model performance is impaired by inconsistency. For the same input text and extraction task, these models provide different answers each time they are queried, even when prompted for the same question. This non-deterministic behavior renders them unreliable for scenarios where consistent and accurate information retrieval is essential.

In contrast, specialized parsers such as LangTec’s E-MailParser exhibit significantly higher accuracy, are fully deterministic in their behaviour and consistently achieve 98 % extraction accuracy across various document formats. This reliability makes a deterministic document-understanding solution like E-MailParser a more dependable solution for information extraction tasks, particularly when dealing with diverse e-mail content in business-critical applications.

Conclusion

While LLMs like ChatGPT are excellent for generating content, they have notable limitations, particularly in scenarios requiring deterministic output such as information extraction tasks. For such applications, document-understanding solutions like LangTec’s E-MailParser offer a more reliable and accurate solution.

The topic of the Maritime Cluster Norddeutschland event on April 23 was “Innovative algorithms for shipping and logistics: How automatic text extraction and quantum computing will change business processes”. 40 participants met in the premises of the Business Club Hamburg, the Villa im Heinepark on Elbchaussee to hear fascinating presentations about the promises of digitisation in the shipping industry.

Jan Herberg, CEO of our partner of many years Herberg Systems GmbH, showed how automatic information extraction from email requests enables the digitisation of workflows for shipping logistics. Dr. Kilian Foth, Team Lead Text Analytics at LangTec demo’ed LangTec’s EmailReader and showed how AI-based semantic text analysis can obtain structured business data from various kinds of unstructured documents and messages.

Oliver Szal and Joshua Dibbern from FraunhoferCML showed that competitive quantum computing has already arrived: the audience chose the parameters of a “Maritime Inventory Routing Problem” that was then solved twice over (locally and by a quadratic annealer in Canada) with the same time budget, and the quantum algorithm D-WAVE found the higher-value solution than classical CPLEX optimization.

Protein Folding is a prime example of how rapidly AI can bring technological advances in numerous fields. To witness this, two LangTec team members, Maximilian and Pat, attended the FoldForum II event.

FoldForum II was hosted by a cooperation of AUFBRUCH.Hamburg and Artificial Intelligence Center Hamburg (Aric e.V.) at the DeepTech Campus. As with the first FoldForum event, this cooperation has been a great host and the DeepTech Campus alone is worth a visit for it’s striking appearance and new, comfortable interior.

After Dr. Natalie Rotermund from Aric e.V. and Dr. Dr. Alexander El Gammal from AUFBRUCH.Hamburg introduced the event and the speakers, Dr. Felix Tobola from Aric e.V. started the talks with an in-depth overview of what protein folding is and how it works. He created many moments of insights with his very visual presentation. His talk was followed by another great talk by Dr. Kilian Guse and Head of Bioinformatics Brian Dawson from GQ Bio Therapeutics. They showed how this new technology can be creatively used to design pharmaceutical products, presenting astonishing technology which would probably only be found in science fiction novels just a few years ago.

A highlight was the following panel discussion between the different speakers as well as the audience. Topics ranged from technical details of the AI models to philosophical questions about the epistemic implications of AI-based protein folding for academic research, driven by the manifold interests and backgrounds of the audience.

We would like to thank Aric e.V. and AUFBRUCH.Hamburg for hosting such an inspiring event with so many knowledgeable speakers and are looking forward to future events in this series!

Both public tenders and project offerings are published with high update frequency on a wide range of online portals. Companies therefore need to check multiple portals continually for new entries and updates if they do not want to miss out. Additionally, one usually performs multiple searches with different query terms, such that the effective number of queries to each portal quickly multiplies. Scanning results ploughing through large number of results, often already seen in previous queries. To be effective, this manual search needs to be performed regularly and tends to be extremely tedious and time-consuming.

To help with that, LangTec has developed a crawler-based solution that fully automates this process. The result is a periodic e-mail update, which presents a clear summary of all new entries found across all portals for the user’s personalised search terms. This allows for a much faster response to new public tenders and project offers and removes the effort of manual search.

Initially, LangTec developed this solution for internal use only. To registered users the service now is also available as a subscribable, commercial service. The selection and number of search terms is fully customisable and the same holds for the set of portals scraped and the e-mail update intervals. Feel free to reach out to us  any time in case this sounds interesting to you.

Hosted by the tekom Germany Spring Convention in picturesque Freiburg, together with our business partner parson AG, we gave an interesting talk on use cases of applied AI in technical documentation. The topical focus of this presentation were the many different tools and methods that AI offers these days, and how they can be applied to specific challenges in technical documentation.

We’d like to extend a big ‘Thank you!’ to all participants for the inspiring questions and discussions that followed the talk. Certainly after the presentation it was very clear to everyone that when it comes to automation AI features as a sophisticated Swiss army knife rather than a crude mallet. Being in the know of precisely which AI tool to unfold for which use case empowers you to solve even complex automation challenges effectively and efficiently. It goes without saying, that LangTec is always more than happy to support in such situations 🙂