Portal:Computational Linguistics

From Glottopedia
Jump to navigation Jump to search
This portal presents the most central topics in Computational Linguistics.

Language Analysis

Natural Language Generation


Question Answering

Text Data Mining

Topic Detection

Information Extraction

Information Extraction is a text data mining subfield. It belongs in the Text Analytics family of tools where unstructured text is automatically analyzed for the recognition and extraction of named entities, facts, events, and structured relationships between any of the above. Popular commercial Information Extraction software includes SRA's NetOwl, Inxight's (now SAP) ThingFinder, and ClearForest's (now Reuters) Calais. The current benchmarks set the standard pretty high. Information Extraction software is expected to perform certain (traditionally "hard") NLP tasks such as anaphoric coreference resolution and word sense disambiguation.

Information Retrieval



Mathematical Methods

Language Resources


Information Sources and Conferences

Journals: Cognition , Computational Linguistics , Information Retrieval  Research on Language and Computation , Journal of Logic and Computation , Journal of Logic, Language and Information , Natural Language Engineering , Machine Translation
Conferences: ACL , COLING , EACL , HLT , NAACL


ACL (Association for Computational Linguistics)
EACL (European Chapter of the ACL)
ACM (Association for Computing Machinery)
EAMT (European Association for Machine Translation)
ELRA (European Language Resources Association)
ELSNET (European Network in Language and Speech)
EURALEX (European Association for Lexicography)
LDC (Linguistic Data Consortium)
SALT (Speech and Language Technology, United Kingdom)
TEI (Text Encoding Initiative)

This portal is maintained by Jürgen Wedekind. Please use the discussions tab or Email

to enter your comments, critical remarks, or suggestions. Thank you.