... Association for Computational Linguistics:shortpapers, pages 53–57,
Portland, Oregon, June 19-24, 2011.
c
2011 Association for Computational Linguistics
Latent Class Transliteration based on Source Language ... to 1/K. Based on the preliminary results, we
repeated EM iterations for 40 times.
5.2 Results
Language Class Detection We firstly show the
precision of language d...
... and construc-
tion domains (fields), respectively.
To sum up, the organization module classifies term
descriptions based on domains, for which we use do-
main and description models. In Section 3, ... extraction but generation of ency-
clopedic knowledge.
Section 2 explains the overall design of our ency-
clopedia generation system, and Section 3 elaborates
on our organization model. Sect...
... gene expression at 1 l
M
or higher
concentration of RG-102240, 0.04 l
M
or higher concentra-
tion of RG-102317, 5 l
M
or higher concentration of PonA
and 25 l
M
or higher concentration of MurA ... doi:10.1046/j.1432-1033.2003.03501.x
induction response after addition of an inducer (d) rapid
switch-off response after removal of an inducer (e) repeated
on and off responses (f) specific respons...
... combination of
the weights of insertion, deletion and substi-
tution. The relation is shown in equation (2),
where ins, del and sub are the appearance times
of insertions, deletions and substitutions, ... form of exam-
ination.
In this paper, our evaluation objects are the oral
English picture compositions in English as a Sec-
ond Language (ESL) examination. This examina-
tion requires stud...
... canonical
stress pattern and syllable identity that can be eas-
ily acquired from the output of conventional ASR
and pronunciation dictionary. We treat pitch-accent
detection as a binary classification ... normalized
current duration and the following one.
In the above description, we assumed that the
event of a syllable is only dependent on its observa-
tions, and did not consider contextua...
... sentence
compression based on syntactic or heuristic rules.
McDonald (2007) formulated text summariza-
tion as a knapsack problem and obtained the
global solution and its approximate solutions. Its
relation ... sentences) in given doc-
uments. There are two types of summarization
tasks: single-document summarization and multi-
document summarization. While single-document
summarization...
... small and contains only noun-noun pairs con-
nected by either synonymy or hypernymy. Gur350
contains nouns, verbs and adjectives that are con-
nected by classical and non-classical relations (Mor-
ris ... that Gur65
contains only noun-noun word pairs connected by
classical semantic relations, while the other datasets
also contain cross part-of-speech pairs connected by
non-classical relations...
... the
functionality of summarization and content -based
retrieval of tagged documents.
This paper focuses on summarization based on
this system. The main features of our summariza-
tion method ... their documents as
part of content authoring. This paper discusses au-
tomatic text summarization based on GDA. Its main
features are a domain/style-free algorithm and per-
sonaliz...
... systems, is based on
the following assumptions:
- Preference is a method which, on the basis of
some preference criteria, chooses the best one
among a set of possible interpretations
which ... correspondin~ (sub)trees (from here
on, (sub)tree will be used m the sense of a repre-
sentation of an interpretation or a part ot m~s
representation). A unary rule picks up a (sub)tree
o...