AUEB's Natural Language Processing Group
AUEB's Natural Language Processing Group develops algorithms, models, and systems that allow computers to process and generate natural language texts.The group's current research interests include:
- natural language question-answering systems for document collections, databases, and ontologies,
- textual entailment and paraphrasing,
- text summarization, including query-focused summarization and sentence compression,
- generation of natural language documents from databases and ontologies, especially Semantic Web ontologies,
- document classification, including hierarchical text classification and spam filtering,
- statistical machine translation, especially to and from Greek,
- natural language processing tools, such as named-entity recognizers and part-of-speech taggers,
- machine learning in natural language processing.
AUEB's Department of Informatics co-organized the 12th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2009). The group participated in the organization of the 2nd Pascal Challenge on Large Scale Hierarchical Text classification (LSHTC2) and the 3rd Pascal Challenge on Large Scale Hierarchical Text Classification (LSHTC3), which was also the ECML/PKDD 2012 Discovery Challenge.
Vangelis Pterneas and George Karakatsiotis, members of the group, won the interoperability challenge of Microsoft's Imagine Cup 2011. Their system, Touring Machine (video), uses the NaturalOWL text generation engine, which is freely available.