Semantic Representation

In recent years, there has been renewed interest in the NLP community in genuine language understanding and dialogue. Thus the long-standing issue of how the semantic content of language should be represented is reentering the communal discussion. This paper provides a brief “opinionated survey” of broadcoverage semantic representation (SR). It suggests multiple desiderata for such representations, and then outlines more than a dozen approaches to SR–some longstanding, and some more recent, providing quick characterizations, pros, cons, and some comments on implementations.

Authors

• Lenhart Schubert

Keywords

No keywords are indexed for this paper.