Semantic Role Labeling

This is a technical problem related to one of the term projects in Information Extraction 10-707 in Fall 2010.

Semantic role labeling is a task of detecting the semantic arguments of a sentence. Typical semantic arguments are usually about roles related with the predicate or verb of a sentence such as agent, patient, and instrument. Recognizing and labeling semantic arguments is relatively domain-independent, and could be important in all NLP tasks such like Information extraction and Question Answering.

History

Semantic role labeling has been studied as shared tasks at CoNLL-2004 and CoNLL-2005 [1].

Details

The following sentence, taken from the PropBank corpus, shows the semantic role labeling.

[A0 He ] [AM-MOD would ] [AM-NEG n't ] [V accept ] [A1 anything of value ] from [A2 those he was writing about ] .

existing corpora

• FrameNet[2]
• PropBank [3]

State of the art

• rely on hand-developed grammars

- data-driven techniques

Related Paper

The Gildea and Jurafsky Computational Linguistics 2002 is a paper solving the semantic role labeling problem.

References/Links

• Wikipedia article on Semantic Role Labeling - [4]
• CCG - Illinois Semantic Role Labeling Demo - [5]
• CoNLL-2004 and CoNLL-2005 Shared Tasks - [6]