... both natural language understanding and
advice generation in the domain of narrative in-
struction. The background application is a fully
automated plot analysis agent to improve the writ-
ing ... from each plot rat-
ing level using the “Adventure Corpus.” This pro-
duced matching advice for each story, for a total
of 80 advice statements.
5.3 Advice Rating
An advice rat...
... thorough
domain understanding. On the other hand, our ap-
proach maintains the joint modeling advantage, but
our model is built over simple, domain-independent
features. We also propose and analyze a richer ... protein TNF-alpha receptor type II is
an argument in both a BINDING event (binding) and
in a NEGATIVE REGULATION event (inactivation).
As a consequence of this step, 4.7% o...
... architecture with a control structure;
all the application-dependent information is stored
in a variation of Augmented Transition Networks
(ATNs) called Dialogue Action Forms (DAFs).
These DAFs ... reali-
sation, and in particular, makes integrated use of n-
gram scoring of possible realisations in its chart re-
alisation algorithm (White, 2004; White, 2005). The
n-gram scoring allo...
... relevance
weights on the corpus, rather than a binary partition.
3. Pattern Ranking: Every pattern appearing in
a relevant document is a candidate pattern. Assign
a score to each candidate; the ... this, we introduce a pa-
rameter, : rather than acquiring a single pattern
on each iteration, each learner may acquire up to
patterns (3 in this paper), as long as their scores are...
... obtain transfer rules from case-frame
representations of simple sentences with a
thesaurus for generalization (Akiba et. al., 1996
and Tanaka, 1995); (2) approaches using
structural matching: ...
bilingual dictionary for transfer.
A bilingual dictionary consists of rules that
map a part of the representation of a source
sentence to a target representation by taking
grammatic...
... Events, and
Relations
An important property of a natural language system
is that it often has only partial information about the
individuals (objects, events, and relations) that are talked
about. ... representation by introducing the
predicate
ROLE
and making rolenames into individuals
in the domain.
ROLE(o, r, v)
asserts that individual o has
a role named r that is filled wi...
... ambiguous between being
an auxiliary, a main verb, or a noun and thus there is variation
in the way
can
would be tagged in
I can play the piano, I can
tuna for a living,
and
Pass me a can ... variation n-gram ap-
proach, that variation in annotation can indicate
an annotation error, essentially is also the start-
ing point of the approach to annotation error de-
tection of...
... generation of contrastive
accent and propose an alternative method
that is feasible and computationally at-
tractive in data-to-speech systems.
1 Motivation
The placement of pitch accent plays ... typed data structure containing data on a soccer
match. So-called syntactic templates (van Deemter
and Odijk, 1995) are used to express parts of this
data structure. In GoalGetter, onl...
... Core Language Engine (CLE; A1 -
shawi et al, 198 8a, b) is a domain indepen-
dent system for translating English sen-
tences into formal representations of their
literal meanings which are capable ... although grammaticality
judgments are sometimes variable and
indeterminate, they are much less so
than judgments of semantic acceptabil-
ity, which do not play any part in VEX'...
... grammar.
The grammatical framework in which these
ideas have been implemented is Uaificatioa Cat-
egorial Grammar (UCG) and its semantic repre-
sentation language InL, both developed as part ... descriptions
in the grammar and without having to modify any
implementation code.
2 Types in UCG
Importing the notion of data typing into
unification-based grammars has several advan-
t...