5 Min.

MultiLing 2015: ExB takes high rank in an international Automated Text Summarization competition

ExB’s technology is second only to entries from academic scientists

Computational linguists and engineers of the Munich-based ExB Group have once again demonstrated the power of their intelligent solutions for Cognitive Computing at the prestigious MultiLing competition for Automated Text Summarization.

ExB took part in two of the competitions organized at MultiLing 2015: Multilingual Single Document Summarization (MSS) and Multilingual Multi-Document Summarization (MMS). ExB was the only commercial participant in in the MSS competition, which ranks machine-written summaries of single texts in 38 languages. ExB’s technology scored second against entries from academic institutions in this competition. In the MMS competition, which judges summaries of multiple documents in ten languages, ExB was the only participant to produce summaries in all ten languages. In both competitions, ExB’s entry proved very competitive even against participants that only summarized documents in a few languages, demonstrating the superiority of its cross-language technology.

Veni, vidi, vici – what automated text summarization must do is just what that famous expression does:

Understand the content of a text and reproduce it in as compact a form as feasible. Computational linguists and computer scientists have been working for years to create automated text summarization technologies that could revolutionize scientific work, publishing, and the media and communications industry.

For Dr. Ramin Assadollahi, founder and CEO of ExB, the company’s outstanding performance in this competition confirms that “ExB’s focus on research and development makes it an incubator for scientific advances as well as technological innovations that scale to meet diverse market demands. The objective of our team is to break new ground and to overcome barriers. This requires space and resources – that is what we offer at ExB.”

About Multiling

MultiLing is an initiative to promote and advance automatic multilingual text summarization technology through biennial competitions between systems, providing for the comparison and dissemination of new technologies in this field, and continuously raising the bar for performance. Results of the MultiLing 2015 competition will be officially announced in September 2015 in Prague at the SIGDIAL 2015 conference for computational discourse and dialogue processing technologies.

illustratio-exb-product_demo-g35-loy
One platform,
endless possibilities.

ExB is an Intelligent Document Processing platform that transforms unstructured data from any type of document into structured results. Our AI-based software can not only extract all relevant information from your documents, but also understand them. This allows you to automate your processes and save both time & money, while improving your customer experience and employee satisfaction. Win-win. 

Written by:

Dr. Ramin Assadollahi

CEO & Gründer ExB

Dr. Ramin Assadollahi is a computational linguist, inventor and clinical psychologist and is considered one of the AI thought leaders in Germany.
Stay up to date!

Share this post:

This might also interest you:

 | Events

ExB’s top-tier results in the Camelyon Challenge at ISBI 2016 proves that its image analysis technology is able to handle extremely complex diagnostic tasks. The technology compared systems for identifying cancer in lymph node sections in two tasks.

 | Other

Berlin-based university hospital Charité is using cutting edge ExB technologies in its fibrosis research, in order to automate the analysis of tissue sections for early recognition of pathological changes. Doctor-performed histopathological analysis of liver biopsy samples is currently the gold standard for fibrosis, but is also very time-consuming.

 | Press

Following ExB’s sensational performance at the MICCAI/GlaS Challenge last year, the company’s image processing technology continues its winning streak in international competitions at the ISIC Challenge for automated skin lesion analysis and melanoma detection.

Kostenloser Download:

Whitepaper: Lohnt sich KI?

Sieben typische Fragen über KI beantwortet:

  1. Kann uns KI dabei helfen, unsere eingespielten Prozesse zu digitalisieren?
  2. Gibt es bereits KI-Lösungen für administrative Prozesse?
  3. Was ist der Unterschied von OCR und KI?
  4. Worin besteht der Unterschied zwischen regelbasierten und KI-Lösungen?
  5. Können historische Daten zum Antrainieren verwendet werden?
  6. Muss KI-gestützte Dokumentenverarbeitung immer teuer sein?
  7. Wie berechnet man die Kosten und den ROI eines KI-Projekts?

Laden Sie hier gleich Ihr kostenloses Whitepaper-Exemplar herunter und erfahren Sie die Antworten auf diese Fragen!