finin@prc.unisys.com (Tim Finin) (10/03/89)
AI SEMINAR
UNISYS PAOLI RESEARCH CENTER
Speech Act Interpretation:
Linguistic Structure meets Knowledge Representation
James F. Allen
University of Rochester
One of the crucial problems facing natural language research is the
interpretation of language in context. This requires not only
sophisticated systems to analyze the underlying structure of language,
but also the representation of general knowledge about the world, and
the modelling of natural inference processes. In this talk I will look
at one particular problem that requires both structural constraints
and inference in order to identify the correct interpretation, namely
the identification of the intentions of the speaker. This area of
research often falls under the heading of indirect speech act
recognition. I will argue, however, that the distinction between
literal speech acts and indirect speech acts is impossible to make,
since both notions depend critically on contextual interpretation. I
will then describe a system that uses syntactic and semantic clues to
the speech act as well as inferential processes embodying the context,
to produce a range of acceptable interpretations.
11:00am October 6
BIC Conference Room
Unisys Paoli Research Center
Route 252 and Central Ave.
Paoli PA 19311
-- non-Unisys visitors who are interested in attending should --
-- send email to finin@prc.unisys.com or call 215-648-7446 --
--
______________________________________________________________________________
Tim Finin finin@prc.unisys.com (internet)
Unisys Paoli Research Center ..!{psuvax1,sdcrdcf,cbmvax}!burdvax!finin (uucp)
PO Box 517 215-648-7446 (office), 215-386-1749 (home),eliot@phoenix.Princeton.EDU (Eliot Handelman) (10/05/89)
In article <11627@burdvax.PRC.Unisys.COM> finin@prc.unisys.com (Tim Finin) writes:
; Linguistic Structure meets Knowledge Representation
; James F. Allen
; University of Rochester
;One of the crucial problems facing natural language research is the
;interpretation of language in context. This requires not only
;sophisticated systems to analyze the underlying structure of language,
;but also the representation of general knowledge about the world, and
;the modelling of natural inference processes. In this talk I will look
;at one particular problem that requires both structural constraints
;and inference in order to identify the correct interpretation, namely
;the identification of the intentions of the speaker.
Evidently Artificial Intelligence has not yet met Jacques Derrida.