Tài liệu Báo cáo khoa học: "Unsupervised Relation Disambiguation Using Spectral Clustering" ppt
Tài liệu Báo cáo khoa học: "Unsupervised Relation Disambiguation Using Spectral Clustering" ppt
... clustering result using K-means; (c) Three
elongated clusters in the 2D clustering space using
Spectral clustering: two dominant eigenvectors; (d)
The clustering result using Spectral- based clustering
(σ
2
=0.05). ... been
tagged relation types in the given corpus. Then the
relation type tags were removed to test the unsuper-
vised relation disambiguation. During the evalua-...
Tài liệu Báo cáo khoa học: "Identifying Text Polarity Using Random Walks" pptx
... the
performance using 10-fold cross validation. The
table shows that the proposed method outperforms
the spin model. The spin model approach uses
word glosses, WordNet synonym, hypernym, and
antonym relations, ... achieves better performance by only using
WordNet synonym, hypernym and similar to rela-
tions. Adding co-occurrence statistics slightly im-
proved performance, while using gl...
Tài liệu Báo cáo khoa học: "Generating research websites using summarisation techniques" pptx
... 5–8,
Columbus, June 2008.
c
2008 Association for Computational Linguistics
Generating research websites using summarisation techniques
Advaith Siddharthan & Ann Copestake
Natural Language and Information ... stylesheets are often considered inappropriate
for diverse organisations.
Research summary pages using stylesheets can
offer alternative methods of information access and
browsin...
Tài liệu Báo cáo khoa học: " Word Translation Disambiguation Using Bilingual Bootstrapping" doc
... decision (a label).
Many methods for word sense disambiguation
using a supervised learning technique have been
proposed. They include those using Naïve Bayes
(Gale et al. 1992a), Decision ... Bilingual Bootstrapping
3.1 Overview
Instead of using Monolingual Bootstrapping, we
propose a new method for word translation
disambiguation using Bilingual Bootstrapping.
In transla...
Tài liệu Báo cáo khoa học: "Unsupervised Semantic Role Induction with Global Role Ordering" doc
... constituent inde-
pendently of others, and only modeled limited cor-
relations among roles in a sequence (Toutanova et
al., 2008). The correlations have been modeled via
role sets (Gildea and Jurafsky, ... primary
roles, and each interval generates a sequence
of secondary roles and syntactic constituents
using local features. The global role ordering
consists of the sequence of primary role...
Tài liệu Báo cáo khoa học: "Unsupervised Discourse Segmentation of Documents with Inherently Parallel Structure" pdf
... or an abstract and a body,
or parts presenting alternative views on
the same problem. Revealing relations be-
tween the parts by jointly segmenting and
predicting links between the segments,
would ... discussions. Segmentation of these par-
allel parts into coherent fragments and discovery
of hidden relations between them would facilitate
the development of better user interfaces and im-
prov...
Tài liệu Báo cáo khoa học: "Unsupervised Search for The Optimal Segmentation for Statistical Machine Translation" doc
... plots of Morfessor and
Morfessor-bi. Correlation coefficients are -0.005
and -0.279, respectively.
trained on the English side of the training cor-
pus using the SRILM toolkit (Stolcke, 2002). ... Morfessor cost metric has almost
no correlation. Yet, the strong noise in the BLEU
scores (vertical variation in Fig. 2) diminishes the
effect of this correlation, which explains the incon-
sistenc...
Tài liệu Báo cáo khoa học: "Unsupervised Translation Induction for Chinese Abbreviations using Monolingual Corpora" ppt
... phrase-based MT.
4.4 Precision on Full-abbreviation Relations
Table 4 reports the precision on the extracted full-
abbreviation relations. We classify the relations into
several classes based on their ... of the rela-
tions in the given class among all the relations we
have extracted (i.e., 51K relations). For each class,
we randomly select 100 relations, manually tag them
as correct or wrong...
Tài liệu Báo cáo khoa học: "Unsupervised Topic Modelling for Multi-Party Spoken Discourse" ppt
... (presentation, briefing, discus-
sion etc.), rather than the topic or subject matter.
While we expect some correlation between these
two types of segmentation, they are clearly differ-
ent problems. However, ... denominator is intractable.
Consequently, we sample from the posterior dis-
tribution P (z, c|w) using Markov chain Monte
Carlo (MCMC) (Gilks et al., 1996). We use Gibbs
sampling, dr...
