... of the prepo-
sitions (especially of/ de) to the semantic classes adds
to the complexity of the interpretation task. Thus,
for the interpretation of these constructions a system
must rely on the ... 85% of the cases (again, with the exception of
Romanian – 50%). It is interesting to note here that
some of the English NPs are translated into both
noun noun...
... pizza
with anchovies, the PP with anchovies could attach
either to the verb (c.f. ate with anchovies) or to the
noun (c.f. pizza with anchovies), of which the noun
is the correct attachment site. With ... interpretation of this result is that the approach
of annotating all occurrences of the same word with
the same sense allows the model to avoid t...
... compared the result of the recog-
nizers with and without filtering using only 2000
sentences as the training data. Table 5 shows the
result of the total system with different filtering
thresholds. The ... 10). The results of McNemar’s test suggest
that the system with chunk features is significantly
better than the system without it (the p-value is
less than 1.0 &...
... a noun- noun similarity score,
Seen(v
d
) is the set of seen head words filling the
slot v
d
during training, and C(v
d
, n) is the num-
ber of times the noun n was seen filling the slot v
d
The ... co-occurrence count with the verb is cho-
sen. As with the other models, if the two nouns
have the same counts, it randomly guesses.
The smoothing model is named Erk...
... lexicon of the tar-
get grammar,
4
and make use of the existing sets of
4
When the lexicon is less accurate, I can determine the
number of clusters using other algorithms (Hamerly, 2003).
SCFs for the ... c
m
. I then initialize the num-
ber of clusters k to the number of c
m
.
I finally update the acquired SCFs using the ob-
tained clusters and the confidence va...
...
force(s) of an utterance. The goal of such a theory is
to formalize the set of possible plans underlying the use
of particular speech acts Co achieve a given set of goals.
In light of the independent ... pass the salt.
The remainder of this paper attempts to illustrate the
kinds of predictlons made by the theory,.and the use of
anaphora to support one...
... cases where the
query is composed of two or more sentences, we
compute the similarity between the document sen-
tence (s) and each of the query-sentences (q
i
) then
we take the average of the scores.
3 ... between The
hero killed the villain” and The villain killed the
hero”. The task like answering complex questions
that requires the use of more complex syntact...
... number of sentences
in the sample, and the % column gives the sample
size as a percentage of the whole section.
We compare the CCG parser to the Berkeley
parser using the accurate mode of the Berke-
ley ... underestimated, when the evaluation frame-
work is such that incremental improvements of a
few tenths of a percent are routinely presented as
improving the st...
... layouts, there is a minority
strategy, used by 4% of the speakers (3 out of 72 cases
of the data of Linde (1974)) describing the layout in
the form of a map. The speaker first describes the
outside ... breadth first traversal
with the root being the outside shape, the internal
divisions the next layer of nodes, and the names of
these divisions the t...
... too.
2
Therefore, it would be better to look at whether as-
sessors tend to find the same SCUs (information
“nuggets”) in different summaries on the same topic,
and whether they annotate them consistently. ... manually-annotated
summaries from the same topic, and then we com-
pared the resulting “autoPyramid” score with the
score from the original manual annotation for that
summa...