Báo cáo khoa học: "On Jointly Recognizing and Aligning Bilingual Named Entities" doc
Báo cáo khoa học: "On Jointly Recognizing and Aligning Bilingual Named Entities" doc
... Sweden, 11-16 July 2010.
c
2010 Association for Computational Linguistics
On Jointly Recognizing and Aligning Bilingual Named Entities
Yufeng Chen, Chengqing Zong
Institute of Automation, Chinese ... scores when selecting candi-
dates. From this basis, an integrated model is
thus proposed in this paper to jointly identify
and align bilingual named entities between
C...
Báo cáo khoa học: "On the Evaluation and Comparison of Taggers: the Effect of Noise in Testing Corpora." doc
...
K=(1-C)t+C(1-u)p
(2)
The relationship between the real and the ob-
served performance is derived from 1 and 2:
x=K-C(1-u)p+Cu
Since only K and C are known (or approxi-
mately estimated) we can ... bounds for t, u and
p, and see in which range is x.
Since all variables are probabilities, they are
bounded in [0, 1]. We also can assume 2 that
K > C. We can use this constr...
Báo cáo khoa học: "On Parsing Strategies and Closure" pdf
...
Given
two
noun
phrases
NP 1. NP 2 in a sentence, if NP 1 precedes and
commands NP 2 and NP 2 is not a pronoun, then
NP1 and NP 2 are noncoreferentiaL
It appears t o be impossible to apply ...
finite memory. The rule becomes harder and harder to enforce
as more and more names are mentioned. As the memory
requirements grow, the performance model is less and less likely
t...
Tài liệu Báo cáo khoa học: "ON THE AUTOMATIC TRANSFORMATION OF CLASS MEMBERSHIP CRITERIA" docx
... matching and
for easy handling of inexact matches. We might,
The
research reported in this
paper
was partially
supported
by
the National Science Foundation
under
Grant
#S0C-7811q08 and ...
propositions to be accessed and manipulated (e,go, for
the inexact matching Functions listed above) in an
efficient and straightforward manner. Thus, the
Fulfillment
of
3PECI and...
Báo cáo khoa học: "Integrating Graph-Based and Transition-Based Dependency Parsers" docx
... ad-
jectives, adverbs, adpositions, and conjunctions.
Given that there is a strong negative correlation
between dependency length and tree depth, and
given that nouns and pronouns tend to be more
deeply ... partially processed nodes and a buffer β
c
containing the remaining input. Transitions in such a
system add arcs to the dependency graph and mani-
pulate the stack and buffer...
Báo cáo khoa học: "Modeling Inflection and Word-Formation in SMT" doc
... Computational Linguistics.
John Lafferty, Andrew McCallum, and Fernando
Pereira. 2001. Conditional random fields: Prob-
abilistic models for segmenting and labeling se-
quence data. In Proceedings ... al’s
system might generate the “stem and inflection”
corresponding to and his brother. Viewing and
and his as inflection is problematic since a map-
ping from the English phrase and his...
Báo cáo khoa học: "STRUCTURE OF SENTENCE AND INFERENCING IN QUESTION ANSWERING" docx
... STRUCTURE OF SENTENCE AND INFERENCING IN QUESTION ANSWERING
Eva Haji~ovA and Petr Sgall
Faculty of Mathematics and PhTeics
Charles University
: '. '. ... whether a sibgle meaning is concerned s
which is vague or indistinct (cf. Zwicky
and Sadock, 1975; Kasher and Gabbay, |976}
Keenan, 1978);
(iii) whether a given distribution-
al
restriction ... can be linearized,...
Báo cáo khoa học: "THE IMPERFECTIVE PARADOX AND TRAJECTORY-OF-MOTION EVENTS *" doc
...
sibility of having actual events standing in the
part-of relation to hypothetical super-events. This
treatment extends and refines those of Moens
and Steedman (1988) and Jackendoff (1991), at
least ... restricted case of trajectory-
of-motion events. This treatment extends and re-
fines those of Moens and Steedman (1988) and
Jackendoff (1991). In the second part, I describe...
Báo cáo khoa học: "An Efficient Method for Determining Bilingual Word Classes" doc
... details
are given in (Och and Weber, 1998; Och and Ney,
1999).
We demonstrate results of our bilingual clus-
tering method for two different bilingual corpora
(see Tables 1 and 2). The EUTRANS-I ... functions
n(EIE' )
and
nt(FIE )
can
be combined into one count function
ng(X[Y ) :=
n(XIY)+nt(X[Y ) as
for all words f and all words
e and e' holds
n(fle )...