DFG GRK 1994 Research Training Group AIPHES ("Adaptive Information Preparation from Heterogeneous Sources")

Motivation

The importance of thorough research under tight deadlines is increasing rapidly and the consequences for the quality of the research results are far-reaching, especially in decision-making processes. At the same time, the amount of information is growing exponentially, and there is a continuous increase of complexity, heterogeneity, and a high variation in the quality of electronic information sources.

Goals

The vision of the Research Training Group GRK 1994 AIPHES is to extract structured knowledge from heterogeneous sources using automated means in order to create dossiers of stylistically homogeneous content. 

 

                                    

Methods

GRK 1994 AIPHES develops methods able to adapt to different genres and domains, so that the results can easily be transferred to other tasks and – in later phases of the project – to other user groups and languages. The first project phase focuses on multi-document summarization (MDS) as a prototypical task. As a representative use-case, we choose German documents on educational topics extracted from heavily heterogeneous sources.

Adaptive information processing is a complex task which requires the involvement of researchers from four project areas: (A) the computational linguistic modeling of discourse phenomena in heterogeneous text genres, (B) the development of language technologies for heterogeneous MDS, (C) the representation and analysis of text-induced structures, and (D) the criteria and mechanisms for selecting and assessing the quality of heterogeneous sources and resulting summaries in information management. By investigating these questions in a densely connected research plan, the four research areas will jointly address adaptive information processing both in breadth and depth.The figure below represents the interaction of the four areas and the guiding themes of each area.

Qualification Concept

The qualification concept includes collaborations across disciplines and locations, intensive international networking, scientific consultation of at least two PhD advisors and of one international co-advisor for each doctoral project, and the responsible participation of excellent post-doctoral researchers in doctoral supervision and training jointly with experienced advisors. The graduate program will form a central location for the qualification of young researchers in the highly demanded academic field of adaptive information processing.

Team at UKP

Principal Investigators

  • Prof. Dr. Iryna Gurevych (Speaker)
  • Dr. Christian M. Meyer

Coordination

  • Dr. Sebastian Harrach

Associated Senior Researchers

  • Dr. Richard Eckart de Castilho
  • Prof. Dr. Margot Mieskes (Informationswissenschaft, Hochschule Darmstadt)
  • Dr. Ivan Habernal

Doctoral Researchers

  • Teresa Botschen
  • Andreas Hanselowski
  • Maxime Peyrard
  • Avinesh P.V.S.
  • Tobias Falke

Associated Doctoral Researchers

  • Nils Reimers
  • Daniil Sorokin
  • Christopher Tauchmann

Publications

Additional Attributes

Type

Multimodal Frame Identification with Multilingual Evaluation

Teresa Botschen, Iryna Gurevych, Jan-Christoph Klie, Hatem Mousselly Sergieh, Stefan Roth
In: Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, p. to appear, June 2018
Association for Computational Linguistics
[Inproceedings]

SRL4ORL: Improving Opinion Role Labelling using Multi-task Learning with Semantic Role Labeling

Ana Marasovic, Anette Frank
In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, p. (to appear), June 2018
[Inproceedings]

Which Scores to Predict in Sentence Regression for Text Summarization?

Markus Zopf, Eneldo Loza Mencía, Johannes Fürnkranz
In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, p. (to appear), June 2018
[Inproceedings]

Estimating Summary Quality with Pairwise Preferences

Markus Zopf
In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, p. (to appear), June 2018
Association for Computational Linguistics
[Inproceedings]

Multi-Task Learning for Argumentation Mining in Low-Resource Settings

Claudia Schulz, Steffen Eger, Johannes Daxenberger, Tobias Kahse, Iryna Gurevych
In: Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, p. to appear, June 2018
Association for Computational Linguistics
[Inproceedings]

Objective Function Learning to Match Human Judgements for Optimization-Based Summarization

Maxime Peyrard, Iryna Gurevych
In: Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, p. to appear, June 2018
Association for Computational Linguistics
[Inproceedings]

auto-hMDS: Automatic Construction of a Large Heterogeneous Multilingual Multi-Document Summarization Corpus

Markus Zopf
In: Proceedings of the 11th edition of the Language Resources and Evaluation Conference (LREC 2018), p. (to appear), May 2018
[Inproceedings]

Concatenated p-mean Word Embeddings as Universal Cross-Lingual Sentence Representations

Andreas Rücklé, Steffen Eger, Maxime Peyrard, Iryna Gurevych
In: arXiv, March 2018
[Online-Edition: https://arxiv.org/abs/1803.01400]
[Article]

Kollaborative Lexikographie: Strukturen, Dynamik und Zusammensetzung gemeinschaftlich erarbeiteter Wortschätze

Christian M. Meyer
In: Wortschätze: Dynamik, Muster, Komplexität, Vol. 2017, p. 293-310, February 2018
Berlin/Boston: De Gruyter
[Online-Edition: https://www.degruyter.com/view/books/9783110579963/9783110579963-016/9783110579963-016.xml]
[InCollection]

Event Time Extraction with a Decision Tree of Neural Classifiers

Nils Reimers, Nazanin Dehghani, Iryna Gurevych
In: Transactions of the Association for Computational Linguistics, Vol. 6, p. 77-89, 2018
[Online-Edition: https://github.com/UKPLab/tacl2017-event-time-extraction]
[Article]

Funding

This project is funded by Deutsche Forschungsgemeinschaft (German Research Foundation).

Further Information

Detailed information on GRK 1994 AIPHES can be found it its web site: https://www.aiphes.tu-darmstadt.de

A A A | Drucken Print | Impressum Impressum | Sitemap Sitemap | Suche Search | Kontakt Contact | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang