... ∗]
(1)
3.4 Translation Induction for Chinese
Abbreviations
Given a Chinese abbreviation and its full-form, we
induce English translation entries for the abbrevia-
tion by using the full-form as ... the
full-form, so it is being generalized.
3 Unsupervised Translation Induction for
Chinese Abbreviations
In this section, we describe an unsupervised method
to induce...
... Association for Computational Linguistics
Unsupervised Topic Modelling for Multi-Party Spoken Discourse
Matthew Purver
CSLI
Stanford University
Stanford, CA 94305, USA
mpurver@stanford.edu
Konrad ... desired general level of granularity. For each
set of annotations, we therefore performed two
sets of segmentations: one in which the threshold
was set for each meeting to give the known...
... 37–42,
Prague, June 2007.
c
2007 Association for Computational Linguistics
Kinds of Features for Chinese Opinionated Information Retrieval
Taras Zagibalov
Department of Informatics
University of Sussex
United ... politics.
We therefore believe that a system capable of pro-
viding access to opinionated information in other
languages (especially in Chinese) might be of great
use for i...
... variation, 83.04%. For
comparison purposes, we also computed the value
of R
2
for adequacy using the BLEU score formula
given in (Papineni et al., 2002), for the 7 systems
using the same one ... comparison
purposes, we also computed the value of R
2
for
fluency using the BLEU score formula given in
(Papineni et al., 2002), for the 7 systems using the
same one referenc...
... cor-
pus using the SRILM toolkit (Stolcke, 2002). The
BLEU metric (Papineni et al., 2002) was used for
translation evaluation.
Figure 1 compares the translation performance
obtained using the ... which
unexpectedly improves the translation per-
formance as measured by BLEU.
1 Introduction
In statistical machine translation (SMT), words
are normally considered as the building blo...
... systems are built using labelled train-
ing data or using heuristics to extract transliteration
pairs. These systems are language pair dependent or
require labelled information for training. Our ... of the Association for Computational Linguistics, pages 469–477,
Jeju, Republic of Korea, 8-14 July 2012.
c
2012 Association for Computational Linguistics
A Statistical Model for Unsu...
... PARAMETERS —————–
for all predicate p do
for all voice vc ∈ {active, passive} do
draw θ
order
p,vc
∼ Dirichlet(α
order
)
for all interval I do
draw θ
SR
p,I
∼ Dirichlet(α
SR
)
for all adjacency ... the ordering of core roles is important
information for SRL systems, and (ii) the intervals
bounded by core roles provide good context infor-
mation for classification of other roles.
4...
... (WSD) techniques in
SMT for translation selection. However, WSD techniques
for SMT do so indirectly, using source-side context to help
select a particular translation for a source rule.
s
ource
... addi-
tional features of the translation model to im-
prove translation performance. Significant im-
provements are obtained over a state-of-the-art
hierarchical phrase-based...
... proportions β
(k)
∼
GEM(α
(k)
) for k ∈ {1, . . . , K}.
• Choose the part-specific language models φ
(k)
i
∼
Dir(γ
(k)
) for k ∈ {1, . . . , K} and i ∈ {1, 2, . . .}.
• For each part k and each sentence ... at learning time using non-informative
hyperpriors (as we do in our experiments), or set
manually to indicate preferences of segmentation
granularity.
At inference time, we enforce...
... Sweden, 13 July 2010.
c
2010 Association for Computational Linguistics
Sentiment Translation through Lexicon Induction
Christian Scheible
Institute for Natural Language Processing
University ... with
sentiment information, and the information is then
projected to the target language. Problems arise
due to mistranslations, e.g., because irony is not
recognized.
Banea et al. (2008) use...