Dr. Tim Polzehl
- High-quality data collection via crowdsourcing
- Data management and data services via crowdsourcing (clean, index, verify, tag, label, translate, summarize, join, etc. )
- Data synthesis und data generation via crowdsourcing
- Subjective influences and bias normalization in crowdsourcing
- Crowd-creation, crowd-voting, crowd-storming, crowd-testing applications
- Crowdsourcing service for machine learning and BI
- Crowdsourcing business and Business Logic
- Complex automated workflows: combining human and artificial intelligence
- Crowdsourcing with mobile devices
- Real-time crowdsourcing
- Skill-based crowdsourcing and verification of crowd-experts
- Automatic user classification
- Automatic speaker characterization (age, gender, emotion, personality)
- Automatic speech recognition (ASR),
- Prosody and voice gesture recognition
- Prosodic voice print analysis, phonetic science
- App development with speech functionalities (Android, iOS)
Text Classification, Natural Language Processing (NLP)
- Sentiment Analysis
- Affective Analysis, Emotion
- Personality und Lifestyle Detection from Social-Networks (Twitter, FB, G+, etc.)
Machine Learning and Artificial Intelligence
- Automated user modelling
- Classification and prediction systems using linear and non-linear algorithms
- Feature selection and reduction
- Evaluation and verification methods
Running and Past Projects:
please click here.
Tim Polzehl studied Science of Communication at Berlin's Technical University. Combining linguistic knowledge with signal processing skills he focused on speech interpretation and automatic data- and metadata extraction. He gathered experience within the field of machine learning as exercised when recognizing human speech utterances and classifying emotional expression subliminal in speech, the latter of which became his M.A. thesis.
In 2008 Tim Polzehl started his position as PhD candidate in Telekom Innovation Laboratories (T-Labs) and the Quality and Usability Lab. He worked in both industrial and academic projects with focus on speech technology, App-Development, machine learning crowd sourcing solutions.
2011-2013 Tim was leading a R&D Project for Telekom Innovation Laboratories with Applications in the field of Intelligent Customer-Care Systems and Speech-Apps .
2012-2014 Tim was awarded with an BMBF funded Education program for future IT and Development Leadership involving SAP, Software AG, Scheer Group, Siemens, Holtzbrinck, Bosch, Datev and Deutsche Telekom AG, amongst highly ranked academic institution (Softwarecampus ).
2014 Tim was awarded the PhD for his work on automatic prediction of personality attributes from speech.
Since 2014 Tim has been working as a Postdoc at the Quality and Usability chair of TU-Berlin. At the same time Tim is driving the start-up activity applying the earlier development of crowdsourcing solutions Crowdee .
Quality and Usability Labs
Technische Universität Berlin
Tel.:+49 (30) 8353-58227Fax: +49 (30) 8353-58409mailto:email@example.com 
|Author||Iskender, Neslihan and Polzehl, Tim and Möller, Sebastian|
|Title of Book||Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing|
|Publisher||Association for Computational Linguistics|
|Series||HCI + NLP|
|Abstract||In recent years, crowdsourcing has gained much attention from researchers to generate data for the Natural Language Generation (NLG) tools or to evaluate them. However, the quality of crowdsourced data has been questioned repeatedly because of the complexity of NLG tasks and crowd workers' unknown skills. Moreover, crowdsourcing can also be costly and often not feasible for large-scale data generation or evaluation. To overcome these challenges and leverage the complementary strengths of humans and machine tools, we propose a hybrid human-machine workflow designed explicitly for NLG tasks with real-time quality control mechanisms under budget constraints. This hybrid methodology is a powerful tool for achieving high-quality data while preserving efficiency. By combining human and machine intelligence, the proposed workflow decides dynamically on the next step based on the data from previous steps and given constraints. Our goal is to provide not only the theoretical foundations of the hybrid workflow but also to provide its implementation as open-source in future work.|