Advanced Large ­Scale Language Analysis for Social Intelligence Deliberation Support
The research project All-Sides aims at creating a new generation of solutions for collective decision support that are driven by massive forms of digital dialogue. Within the project we develop a prototype of a dialogue support platform called Common Round.
 
The guiding vision is the notion of social intelligence, which aim to trigger advantageous decisions by providing the needed information and background knowledge at the right time, in the right place and in the right form. By educating large communities about the backgrounds and ramifications of plans or proposals and by informing them about the major alternatives together with the associated argumentation and evidence, the foundations are laid for more effective forms of participation and direct democracy. Through these mechanisms for sharing knowledge, information and argumentation associated with alternative viewpoints, new processes of collective reflection and decision will become possible that may in the long run indeed create a form of collective, social intelligence in the stronger sense of intelligence.
 
 

Project Common Round
We  develop  a  prototype  of  an  argumentative dialogue  support  platform  called  Common Round which:

1.     allows to debate topics by giving pro or contra arguments and backing the arguments by evidence,

2.     structures and aggregate the semantic content of debates,

3.     provides background knowledge for the debate topic,

4.     provides crosslingual functionality which allows to translate debates and to search for background knowledge in other languages.

The key methodology is a combination of:

1.     eliciting semantic content and structure from the participants

2.     employing advanced language technologies for the extraction of semantic essence from their contributions and for the aggregation of the detected opinions, proposals, argumentations and evidence.

The envisaged platform will be evaluated in a restricted but realistic scenario. This evaluation will provide directions for further developments after the project in order to eventually reach at a marketable system.

The research and the development of the platform Common Round within the project All-Sides  is carried out by the Language Technology Labs of German Center of Artificial Intelligence (DFKI GmbH).

The project is funded by the Federal Ministry of Education and Research of Germany (01IW14002). 

Publications
Sar-graphs: A Language Resource Connecting Linguistic Knowledge with Semantic Relations from Knowledge Graphs. 
Sebastian Krause; Leonhard Hennig; Andrea Moro; Dirk Weißenborn; Feiyu Xu; Hans Uszkoreit; Roberto Navigli: 
In: Journal of Web Semantics: Science, Services and Agents on the World Wide Web, Vol. Special Issue on Knowledge Graphs, Elsevier, 2016.
 
Relation- and Phrase-level Linking of FrameNet with Sar-graphs. 
Aleksandra Gabryszak; Sebastian Krause; Leonhard Hennig; Feiyu Xu; Hans Uszkoreit 
In: Proceedings of the 10th International Conference on Language Resources and Evaluation. International Conference on Language Resources and Evaluation (LREC-16), May 23-28, Portorož, Slovenia, European Language Resources Association, 2016. 
 
TEG-REP: A corpus of Textual Entailment Graphs based on Relation Extraction Patterns. 
Kathrin Eichler; Feiyu Xu; Hans Uszkoreit; Leonhard Hennig; Sebastian Krause 
In: Proceedings of the 10th International Conference on Language Resources and Evaluation. International Conference on Language Resources and Evaluation (LREC-16), May 23-28, Portorož, Slovenia, European Language Resources Association, 2016. 
 
Event Linking with Sentential Features from Convolutional Neural Networks. 
Sebastian Krause; Feiyu Xu; Hans Uszkoreit; Dirk Weißenborn 
In: Proceedings of the 20th Conference on Computational Natural Language Learning. Conference on Computational Natural Language Learning (CoNLL-16), Association for Computational Linguistics, 2016. 
 
Improvement of n-ary Relation Extraction by Adding Lexical Semantics to Distant-Supervision Rule Learning.
Hong Li; Sebastian Krause; Feiyu Xu; Andrea Moro; Hans Uszkoreit; Roberto Navigli 
In: ICAART 2015 - Proceedings of the 7th International Conference on Agents and Artificial Intelligence. International Conference on Agents and Artificial Intelligence (ICAART-15), 7th, January 10-12, Lisbon, Portugal, SciTePress, 2015. 
 
Idest: Learning a Distributed Representation for Event Patterns. 
Sebastian Krause; Enrique Alfonseca; Katja Filippova; Daniele Pighin 
In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Annual Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL-15), May 31 - June 5, Denver, Colorado, USA, The Association for Computational Linguistics, 2015. 
 
A Web-based Collaborative Evaluation Tool for Automatically Learned Relation Extraction Patterns. 
Leonhard Hennig; Hong Li; Sebastian Krause; Feiyu Xu; Hans Uszkoreit 
In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing -- System Demonstrations. Annual Meeting of the Association for Computational Linguistics (ACL), July 26-31, Beijing, China, ACL, 2015. 
 
Semi-automatic Generation of Multiple-Choice Tests from Mentions of Semantic Relations. 
Renlong Ai; Sebastian Krause; Walter Kasper; Feiyu Xu; Hans Uszkoreit 
In: 2nd Workshop on Natural Language Processing Techniques for Educational Applications (NLP-TEA-2) at ACL-IJCNLP 2015. Workshop on Natural Language Processing Techniques for Educational Applications (NLP-TEA-2), 2nd, located at ACL-IJCNLP 2015, July 31, Beijing, China, ACL, 2015. 
 
Sar-graphs: A Linked Linguistic Knowledge Resource Connecting Facts with Language. 
Sebastian Krause; Leonhard Hennig; Aleksandra Gabryszak; Feiyu Xu; Hans Uszkoreit 
In: Fourth Workshop on Linked Data in Linguistics: Resources and Applications (LDL-2015) at ACL-IJCNLP 2015. Workshop on Linked Data in Linguistics (LDL-2015), 4th, located at ACL-IJCNLP 2015, July 31, Beijing, China, ACL, 2015. 
 
An OWL Ontology for Biographical Knowledge. Representing Time-Dependent Factual Knowledge. 
Hans-Ulrich Krieger; Thierry Declerck 
In: Proceedings of the First Conference on Biographical Data in a Digital World 2015. Biographical Data in a Digital World (BD-2015), April 9, Amsterdam, Netherlands, CEURS-WS.org, 7/2015. 
 

Contact

 

Prof. Dr. Hans Uszkoreit

DFKI Projektbüro Berlin

Alt-Moabit 91c

10559 Berlin

Hans.Uszkoreit@dfki.de

Dr. Feiyu Xu

DFKI Projektbüro Berlin

Alt-Moabit 91c

10559 Berlin

Feiyu.Xu@dfki.de