LT to host the GermEval 2017Shared Task on Aspect-Based Sentiment Analysis
11 September 2017, by Reinhard Zierke
Together with the Language Technology Lab (LTL) from the Universität Duisburg-Essen, we are hosting the GermEval 2017 Shared Task on Aspect-based Sentiment Analysis. In this shared task, we utilize the data, which we annotated as part of the ABSA-DB project with the Deutsche Bahn Fernverkehr AG.
The shared task has the largest dataset among all tasks on Sentiment Analysis. It consits of four subtasks with varying difficulties. Data is provided in two formats for an easy participation. Data and annotation guidelines are available: GermEval 2017 datasets.
The proceedings are available on the website. We provide the task overview paper and the system paper, which -- as the organizer system -- did not take part in the challenge.
- GermEval 2017: Shared Task on Aspect-based Sentiment in Social Media Customer Feedback (Michael Wojatzki, Eugen Ruppert, Sarah Holschneider, Torsten Zesch and Chris Biemann)
- LT-ABSA: An Extensible Open-Source System for Document-Level and Aspect-Based Sentiment Analysis (Eugen Ruppert, Abhishek Kumar and Chris Biemann) -- Code available on the GitHub page: LT-ABSA