summetix (formerly known as ArgumenText) uses Argument Mining to discover hidden insights in your customer's feedback and to monitor and discover tech and innovation trends. summetix GmbH is a Spin-Off of the Ubiquitous Knowledge Processing (UKP) Lab at the Technische Universität Darmstadt.
In the first step, customer feedback is reduced to the core information, i.e. meaningful statements about specific error patterns, but also the strengths of a product.
In the next step, similar groups of such statements are combined into clusters containing repeatedly mentioned product problems and strengths.
Clusters are then correlated with customer feedback metadata like a production date, a product line, or sales market. Based on this, our customers can prepare or adapt specific actions for product development and improvement or communication campaigns.
You can search for new technologies or hot topics around innovaton, but also for products, in thousands of sources.
The most important pro and con arguments will be identified, helping you to quickly understand potentials and risks of any topic of interest.
By analyzing arguments over time, you will get insights about the past developments and potential future tech trends.
The technology behind summetix ("ArgumenText") is based on several years of intense research in multiple areas of Natural Language Processing, Deep Learning and Argument Mining. The results have been published in top-tier scientific venues. Below is an overview of the most important components of our system.
Advanced machine learning techniques ensure high precision in your applications. Details in:
Argument similarity controls a precise and scalable grouping of statements.
Multilingual models are available for your language-dependent document collections. Details in:
Our data partner PressRelations (a company of Handelsblatt Media Group) allows us to access 80,000 global, real-time updated news media sources, as well as social media sources.Website
We are among the 6 awardees of the "Gründungspreis+" in this year's Startup competition of the German Federal Ministry for Economic Affairs and Energy! The jury highlighted the innovation and outstanding service offer of our approach, in combination with substantial saving potential for our customers. You can read more about the competition here.
We have been selected for the highly competitive 6-week accelerator program by EY Startup Academy! Looking forward to another great opportunity to learn and accelerate our growth!
We will be giving a talk at the 5th Hessischer Innovationskongress. The talk will happen as part of the "Hessens BEST" Stream on September 2nd at 15:35. We'll also be available virtually at the event.
We've added new publications accepted at NAACL 2021, SIGDIAL 2021 and a journal paper accepted by the "KI - Künstliche Intelligenz" journal. The paper "From Argument Search to Argumentive Dialogue: A Topic-Independent Approach to Argument Acquisition for Dialogue Systems", co-authored by Johannes Daxenberger won the Best Paper award at SIGDIAL conference!