... words to
the right and left of the verb, identified using POS
tags, represented by has_narrow(snt,
word_ position, word) :
has_narrow(snt
1
, 1st _word_ left, mind).
has_narrow(snt
1
, 1st _word_ right, ... preposition to
the right, 1st and 2nd words to the left and right,
1st noun, 1st adjective, and 1st verb to the left and
right. These are represented using definitions o...
... bilin-
gual word alignment finds word- to -word connec-
tions across languages. Originally introduced as a
byproduct of training statistical translation models
in (Brown et al., 1993), word alignment ... new information resulting in im-
proved alignments.
2 Constrained Alignment
Let an alignment be the complete structure that
connects two parallel sentences, and a link be
one...
... on Word
Alignment
The alignment approach to synonym extraction is
based on automatic word alignment. Context vec-
tors are built from the alignments found in a paral-
lel corpus. Each aligned word ... context
and one using translational context based on word
alignment and the combination of both. For both
approaches, we used a cutoff n for each row in our
word- by-...
... utter-
ances and automatically annotated with part-of-
speech tag and supertag information and named
entities. They were annotated by hand for dia-
log acts and tasks/subtasks. The dialog act and
task/subtask ... types of infor-
mation provide rich clues for building dialog mod-
els (Grosz and Sidner, 1986). Dialog models can
be built ofine (for dialog mining and summari...
... modeling pro-
vides a formal and convenient way of grouping
documents and words to topics. In order to apply
topic models to our problem, we map RASCs to
documents, items to words, and treat the output ... fewer
“documents”, “words”, and “topics”. To further
improve efficiency, we also perform preprocess-
ing (refer to Section 3.4 for details) before build-
ing topic models...
... (Shawe-Taylor
and Cristianini, 2004) and tree kernels (Raymond
and Riccardi, 2007; Moschitti and Bejan, 2004;
Moschitti, 2006) to implicitly encode n-grams and
other structural information in ... param-
eters, models and results of our experiments of
word chunking and concept classification. Our
baseline relates to the error rate of systems based
on only FST and SVMs. The r...
... condi-
tional random fields. We create new train-
ing sets for English and Dutch from the
CELEX European lexical resource, and
achieve error rates for English of less than
0.1% for correctly allowed ... 1,
I(y
i−1
= 1 and y
i
= 0 and x
3
x
4
= ph) = 1.
All other similar functions have value 0:
I(y
i−1
= 1 and y
i
= 1 and x
2
x
3
= yp) = 0,
I(y
i−1
= 1 and y
i
= 0 and x...
... current evaluation metrics,
and suggestions for new metrics. Experiments on
strings and word lattices are reported in Section 5,
and conclusions and opportunities for future work
are outlined ... and bet-
ter models of spoken language (Hall and Johnson,
2003; Roark, 2001; Chelba and Jelinek, 2000).
Our goal is integration of head-driven lexical-
ized parsing with acousti...
... grammatical and pro-
cessing framework for handling the repairs,
hesitations, and other interruptions in nat-
ural human dialog. The proposed frame-
work has proved adequate for a collection ... (urn) and speech re-
pairs (I mean) and give meta-comments on the ut-
terance (right).
specify how speech repairs should be handled
by the parser. (Hindle, 1983) and (Bear et
al...
... Tree-
bank, and Sinorama, is then given to GIZA++ to
perform one word alignment run. It took about 40
hours on our 2.4 GHz machine with 2 GB memory
to perform this alignment.
After word alignment, ... for most of these nouns.
The parallel text alignment approach works
well for nature and sense, among these nouns. For
nature, the parallel text alignment approach gi...