Báo cáo khoa học: "Generative Models for Statistical Parsing with Combinatory Categorial Grammar" pptx
Báo cáo khoa học: "Generative Models for Statistical Parsing with Combinatory Categorial Grammar" pptx
... Generative Models for Statistical Parsing with Combinatory Categorial
Grammar
Julia Hockenmaier and Mark Steedman
Division of Informatics
University of Edinburgh
Edinburgh ... probability models for a wide-
coverage Combinatory Categorial Gram-
mar (CCG) parser. These models are
trained and tested on a corpus obtained by
translating the Penn Treebank trees into
CCG nor...
Báo cáo khoa học: "Distortion Models For Statistical Machine Translation" doc
... Meeting of the ACL, pages 529–536,
Sydney, July 2006.
c
2006 Association for Computational Linguistics
Distortion Models For Statistical Machine Translation
Yaser Al-Onaizan and Kishore Papineni
IBM ... lengths.
These models do not generalize well since their param-
eters are tied toabsolute word positionwithin sentences
which tend to be different for the same words across
senten...
Báo cáo khoa học: "Fertility Models for Statistical Natural Language Understanding" pdf
... in-
crease in performance of about 2-3% for most mod-
els. For General-LM, results increased by 8-10%.
The Poisson and general fertility models show a 2-
5% gain in performance over the basic ... translation probabilities are shown
for the unigram and headword models in table 2.
The formal language words have captured reason-
able English words for their most likely transla-...
Báo cáo khoa học: "Error Detection for Statistical Machine Translation Using Linguistic Features" pptx
... Meeting of the Association for Computational Linguistics, pages 604–611,
Uppsala, Sweden, 11-16 July 2010.
c
2010 Association for Computational Linguistics
Error Detection for Statistical Machine
Translation ... features
alone outperform word posterior probabil-
ity based confidence estimation in error
detection; and 2) linguistic features can
further provide complementary informa-
ti...
Tài liệu Báo cáo khoa học: "Topic Models for Dynamic Translation Model Adaptation" pptx
... opposite
is true, with the LTM models achieving better per-
formance.
6
On the NIST corpus, LTM-10 again achieves the
best gain of approximately 1 BLEU and up to 3 TER.
LTM performs on par with or better ... unseen for a given domain s, we are already
performing an implicit form of smoothing (when
computing the expected counts), since each docu-
ment has a distribution over all topics...
Tài liệu Báo cáo khoa học: "Corpus Expansion for Statistical Machine Translation with Semantic Role Label Substitution Rules" doc
... generative models is more likely to be affected
by the radical change of distributions. Therefore,
we also experimented with force aligning the gener-
ated corpus with the word alignment models trained
baseline ... the Association for Computational Linguistics:shortpapers, pages 294–298,
Portland, Oregon, June 19-24, 2011.
c
2011 Association for Computational Linguistics
Corpus E...
Tài liệu Báo cáo khoa học: "Clause Restructuring for Statistical Machine Translation" ppt
... use of syntactic information is to
employ an existing statistical parsing model as a lan-
guage model within an SMT system. See (Charniak
et al., 2003) for an approach of this form, which
shows ... from 25.2% Bleu
score for a baseline system to 26.8% Bleu score for the system
with reordering, a statistically significant improvement.
1 Introduction
Recent research on statistical m...
Báo cáo khoa học: "Transductive learning for statistical machine translation" potx
... rescoring with ad-
ditional models is performed. The system generates
a 5,000-best list of alternative translations for each
source sentence. These lists are rescored with the
following models: ... was merged with the learned
phrase table in each iteration with a weight of λ =
0.1. This value for λ was found based on cross val-
idation on a development set. We ran the algorithm...
Báo cáo khoa học: "Structured Models for Fine-to-Coarse Sentiment Analysis" pdf
... systems.
1.1 Related Work
The models in this work fall into the broad class of
global structured models, which are typically trained
with structured learning algorithms. Hidden Markov
models (Rabiner, 1989) ... which
helped improve performance.
2.2 Beyond Two-Level Models
To this point, we have focused solely on a model for
two-level fine-to-coarse sentiment analysis not only
for...
Báo cáo khoa học: " New Models for Improving Supertag Disambiguation" pdf
... performance
of supertagging. All of the models presented
here perform smoothing using a Good-Turing dis-
counting technique with Katz's backoff model.
With exceptions where noted, our models ...
tated with detailed supertags for punctuation and
with a different analysis for subordinating conjunc-
tions.
between a head and its dependents dependents
which might not a...