... the
future, we plan to explore phonological context and
use more flexible topological structures to model
acoustic units within our framework.
Acknowledgements
The authors would like to thank Hung-an ... R
39
to denote the t
th
feature frame of the
i
th
utterance. Fig. 1 illustrates how the speech signal
of a single word utterance banana is converted to a
sequence of feature vectors...
... function learning
is turned into a simple binary classification problem,
which can be easily solved by a two-class linear sup-
port vector machine.
4 Integration into SMT system
There are two ways to ... converted to dependency trees us-
ing Stanford Parser (Marneffe et al., 2006). We con-
vert the tokens in training data to lower case, and
re-tokenize the sentences using the same to...
... We would also like to thank
Noah Smith for providing us with his data sets.
Eisner, 2005). Nearly all of these approaches have
one aspect in common: the goal of learning is to
identify the set ... differences hold to a
lesser degree when a partial dictionary is provided.
With MLHMM, different tokens of the same word
type are usually assigned to the same cluster, but
types are assign...
... state of a simple finite-state
automaton that only has two states. The automaton
is set to initial state (q
0
) at the top of a message. It
makes a transition to state (q
1
) when it encounters ... is to
enable the quality and nature of discussions that
occur within an on-line discussion board to be
communicated in a summary to a potential new-
comer or group moderators.
We p...
... first step, 8 anno-
tators were asked to select words to be removed to
compress the sentences. In the second step, 6 an-
notators (different from the first step) were asked
to pick the best one ... propose to use a two-step approach in this pa-
per for sentence compression of spontaneous speech
utterances. The contributions of our work are:
• Our proposed two-step approach allows...
... Syntax-Free Approach to Japanese Sentence Compression
Tsutomu HIRAO, Jun SUZUKI and Hideki ISOZAKI
NTT Communication Science Laboratories, NTT Corp.
2-4 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237 ... alternative to these tree trimming
approaches, sequence-oriented approaches have
been proposed (McDonald, 2006; Nomoto, 2007;
Hori and Furui, 2003; Clarke and Lapata, 2006).
Nomoto (2...
...
“legal” is related to “rule”, which in turn is related
to “mandatory”; that “age” is related to “aged”;
and that “Argentine” is related to “Argentina”. It is
not difficult to see by now that ...
generative story (Figure 1 lists some of the factors
specific to this computation.) The readers familiar
with the statistical machine translation (SMT)
literature should recognize...
... as tailored to the financial do-
main, and some forward-looking exten-
sions to the approach that enables users
to specify classifications on the fly.
1 Introduction
Our goal is to support the ... layoff. A second concern is thus
to enable end users to interpret facts and events
through automated context assessment.
The route we have taken towards this end is to
model the doma...
... ‘Kla goes out to seek Laay in the cane field
and he finds that it is about to walk away.’
The sentence in (17) are split into two SVCs: the
series of V
1
to V
3
and the series of V
4
to V
5
, be-
cause ... gener-
ative power for a particular language by annotating
modalities to the slashes to allow or ban specific
combinatory operations. Due to the page limita-
tion, the multimodal...
...
propose a procedural, rule-based approach to
importance evaluation. This novel approach is
supported by a prototype experimental system,
called importance evaluator, that can deal with
descriptive ...
- it is relevant to the topic of discourse
(Lehnert 1982 and 1984);
it is useful to clarify the relations that
make discourse coherent (Hobbs, 1982);
it relates to the topi...