Ubiquitous Knowledge Processing Lab: Difference between revisions

Revision as of 15:28, 9 June 2010

Revision as of 23:54, 9 June 2010

Line 2:

==Research Activities==

UKP Lab develops [[Natural language processing| natural language processing]] techniques for automatically understanding written text and applies them to information management like [[Information retrieval|information retrieval]], [[Question answering|question answering]], and structuring information in [[Wiki|Wikis]]<ref>[http://www.hessen-it.de/mm/Hessen-IT_NEWS_0308.pdf Hessen-IT News 03/2008]</ref>.

The Ubiquitous Knowledge Processing Lab is among the leading research institutes in the field of utilizing [[Web 2.0|Web 2.0]] content as the source of [[Lexical semantics|lexical semantic]] information for natural language processing (NLP). [[Wikipedia]] and [[Wiktionary]] are employed as collaboratively constructed lexical semantic resources and used to improve expert-built resources like [[WordNet]].

These resources are used to develop semantically enhanced algorithms for information retrieval and question answering. An example is [[Semantic search|semantic search]]: If a user enters the query “pie -fruit” into a search engine, a standard search engine will retrieve pages containing the words “pie” but not the word “fruit”, providing plenty of pages on “apple pie”. An intelligent search engine will “understand” that the user is interested in pie recipes that do not use any type of fruit and retrieve appropriate documents<ref>Example from: [http://www.volkswagenstiftung.de/uploads/media/Impulse_fuer_die_Wissenschaft_2010_gesamt.pdf Impulse für die Wissenschaft 2010 (Volkswagenstiftung)]</ref>.

Further research activities at UKP lab are automatic quality assessment of text, [[Sentiment analysis|sentiment analysis]] and opinion mining.

Research activities are organized into the following research areas:

* Educational natural language processing

Line 13:

* Natural language processing for Wikis

A strong focus at UKP Lab is on utilizing novel natural language processing algorithms in real-life applications. UKP Lab collaborates with partners from academia and industry to improve various application scenarios, such as [[Customer relationship management|customer relationship management]], [[Digital humanities|digital humanities]], [[E-learning|educational applications]], or public security.

==Software==

Line 21:

The Darmstadt Knowledge Processing Software Repository (DKPro) offers robust, ready to use NLP components which are built on top of IBM’s [[Uima|Unstructured Information Management Architecture (UIMA)]] as a common and open [[Software framework|framework]].

DKPro contains basic natural language processing components like [[Part-of-speech tagging|part-of-speech tagging]] and [[Lemmatization|lemmatization]].

Additionally, the package offers components that support the processing of user generated discourse. User generated content contains spelling errors, abbreviations and emoticons which prohibit direct application of standard NLP components. DKPro provides the required preprocessing tools.

=== Wikipedia API ===

The Java Wikipedia Library (JWPL)<ref name="paper">Reference publication: [http://elara.tk.informatik.tu-darmstadt.de/Publications/2008/lrec08_camera_ready.pdf Zesch, Müller, Gurevych: Extracting Lexical Semantic Knowledge from Wikipedia and Wiktionary, Proceedings of LREC 2008]</ref> was also developed at UKP Lab. It is a [[Java (programming language)|Java]]-based [[Application programming interface|application programming interface]] for Wikipedia and allows programmatic access to all information contained in [[Wikipedia]].

=== Wiktionary API ===