Tài liệu Báo cáo khoa học: "Using Smaller Constituents Rather Than Sentences in Active Learning for Japanese Dependency Parsing" docx
Tài liệu Báo cáo khoa học: "Using Smaller Constituents Rather Than Sentences in Active Learning for Japanese Dependency Parsing" docx
... 11-16 July 2010.
c
2010 Association for Computational Linguistics
Using Smaller Constituents Rather Than Sentences
in Active Learning for Japanese Dependency Parsing
Manabu Sassano
Yahoo Japan Corporation
Midtown ... Japan
kuro@i.kyoto-u.ac.jp
Abstract
We investigate active learning methods for
Japanese dependency parsing. We propose
active learning meth...
Tài liệu Báo cáo khoa học: "Bucking the Trend: Large-Scale Cost-Focused Active Learning for Statistical Machine Translation" docx
... Sarkar. 2009. Active
learning for multilingual statistical machine trans-
lation. In Proceedings of the Joint Conference of
the 47th Annual Meeting of the ACL and the 4th In-
ternational Joint Conference ... Association for Computational Linguistics.
Katrin Tomanek and Udo Hahn. 2009. Semi-
supervised active learning for sequence labeling. In
Proceedings of the Joint Confe...
Tài liệu Báo cáo khoa học: "Using adaptor grammars to identify synergies in the unsupervised acquisition of linguistic structure" docx
... these independently. This
suggests that there might be a synergistic interaction
in learning several aspects of linguistic structure si-
multaneously, as compared to learning each kind of
linguistic ... syllable
boundaries combining the advantages of treebank and
bracketed corpora training. In Proceedings of the 39th
Annual Meeting of the Association for Computational
Linguistics.
K...
Tài liệu Báo cáo khoa học: "Using Multiple Sources to Construct a Sentiment Sensitive Thesaurus for Cross-Domain Sentiment Classification" doc
... For the Within-Domain
baseline, we train a binary classifier using the la-
beled data from the target domain. This upper base-
line represents the classification accuracy we could
hope to obtain ... domain. How-
ever, given that it is much cheaper to obtain unla-
beled than labeled data for a target domain, there is
strong potential for improving the performance of
our method in this...
Tài liệu Báo cáo khoa học: Insulin-dependent phosphorylation of DPP IV in liver Evidence for a role of compartmentalized c-Src ppt
... proteinase K.
DPP IV levels following stimulation with insulin
and bpV(phen)
In order to examine changes in DPP IV levels follow-
ing insulin stimulation, rats were injected with the PTP
inhibitor ... membrane restructuring enzymes [56] in
protein targeting is beginning to be perceived. For
instance, one striking example of c-Src location inside
one organelle has been reported for t...
Báo cáo khoa học: "Assessing the Costs of Sampling Methods in Active Learning for Annotation" potx
... June 2008.
c
2008 Association for Computational Linguistics
Assessing the Costs of Sampling Methods in Active Learning for Annotation
Robbie Haertel, Eric Ringger, Kevin Seppi, James Carroll, Peter ... Tree-
bank. More significantly, we make the case
for measuring cost in assessing AL methods.
1 Introduction
Obtaining human annotations for linguistic data is
labor intensive an...
Tài liệu Báo cáo khoa học: "Using Cross-Entity Inference to Improve Event Extraction" docx
...
Jenny Rose Finkel, Trond Grenager and Christopher
Manning. 2005. Incorporating Non-local Information
into Information Extraction Systems by Gibbs Sam-
pling. In Proc. 43rd Annual Meeting of the ... used cross-event informa-
tion within ACE extraction, but only for recovering
implicit time information for events.
Liao and Grishman (2010) propose document
level cross-event inference...
Tài liệu Báo cáo khoa học: "Using Structural Information for Identifying Similar Chinese Characters" pdf
... characters in the
right group in the second row in Figure 3 appears
in different places in the characters.
Lexicographers employ radicals of Chinese
characters to organize Chinese characters into ... to input Chinese characters more
efficiently. The longest Cangjie code for any Chi-
nese character contains no more than five elements.
In the Cangjie codes for “脛” and “徑...
Tài liệu Báo cáo khoa học: "Using Automatically Transcribed Dialogs to Learn User Models in a Spoken Dialog System" doc
... generated dialog
d in each training/test set consisted of a sequence of
values for all the observed and unobserved variables:
d = (S
0
, U
0
, A
0
,
˜
A
0
, . . .).
For a training/test set D, let ... generated syn-
thetic dialogs by following the probabilistic process
depicted in Figure 1. In this way, we were able to
create synthetic training sets of varying sizes, as well
as a tes...
Tài liệu Báo cáo khoa học: "Using Word Support Model to Improve Chinese Input System" ppt
... Science, Aca-
demia Sinica.
Chinese Knowledge Information Processing Group.
1996. A study of Chinese Word Boundaries and
Segmentation Standard for Information proc-
essing (in Chinese). Technical ... Analy-
sis in GOING - An Intelligent Chinese Input
System, Proceedings of the Second Joint Con-
ference of Computational Linguistics, Shiamen,
1993, 338-343.
Hsu, W.L. 1994. Chinese pa...