learning hierarchical translation structure with linguistic annotations
Tài liệu Báo cáo khoa học: "Learning Hierarchical Translation Structure with Linguistic Annotations" ppt
Ngày tải lên :
20/02/2014, 04:20
... of linguistically constrained trans-
lation imposing syntactic parse structure, we opt for
linguistically motivated translation. We learn latent
hierarchical structure, taking advantage of linguistic
annotations ... in translation
BLEU scores.
5 Related Work
In this work, we focus on the combination of
learning latent structure with syntax and linguistic
annotations, exploring the crossroads of machine
learning, ... advancing from structures which mimic lin-
guistic syntax, to learning linguistically aware latent
recursive structures targeting translation, we achieve
significant improvements in translation quality...
- 11
- 478
- 0
Tài liệu Báo cáo khoa học: "Multi-Task Active Learning for Linguistic Annotations" pdf
Ngày tải lên :
20/02/2014, 09:20
... 861–869,
Columbus, Ohio, USA, June 2008.
c
2008 Association for Computational Linguistics
Multi-Task Active Learning for Linguistic Annotations
Roi Reichart
1∗
Katrin Tomanek
2∗
Udo Hahn
2
Ari Rappoport
1
1
Institute ... annotations sup-
plied for a classifier as the annotations for a single
annotation task.
Modern HLT systems often utilize annotations re-
sulting from different tasks. For example, a machine
translation ... 2002), scientific text is annotated with POS tags,
parse trees, and named entities.
In this paper, we introduce multi-task active
learning (MTAL), an active learning paradigm for
multiple annotation...
- 9
- 441
- 0
Báo cáo khoa học: "An Interactive Machine Translation System with Online Learning" pdf
Ngày tải lên :
07/03/2014, 22:20
... and a reordering model.
4 Online Learning
In the online learning paradigm, learning proceeds
as a sequence of trials. In each trial, a sample is
presented to the learning algorithm to be classified.
Once ... Oregon, USA, 21 June 2011.
c
2011 Association for Computational Linguistics
An Interactive Machine Translation System with Online Learning
Daniel Ortiz-Mart
´
ınez, Luis A. Leiva, Vicent Alabau,
Ismael ... to
computer-assisted translation. Computational Lin-
guistics, 35(1):3–28.
N. Cesa-Bianchi, G. Reverberi, and S. Szedmak. 2008.
Online learning algorithms for computer-assisted
translation. Deliverable...
- 6
- 431
- 0
Global Strength Assessment Requirement of Ageing Fixed Offshore Structure with Joint Anomalies
Ngày tải lên :
01/04/2013, 22:44
...
global instability is detected; RSR of the structure is retrieved at the structure s collapse point.
In this paper, a 3-legged fixed offshore structure with joint anomalies is selected for ultimate ... ageing 3-legged
structure to demonstrate that the platform has adequate strength and stability to withstand the
specified loading criteria with the identified joint anomalies, but without collapse. ...
Keywords: Ageing structure, Integrity, Non-linear plastic collapse analysis, Reserve strength
ratio
Global Strength Requirement of Ageing Fixed Offshore Structure with Joint...
- 11
- 510
- 0
Tài liệu Báo cáo khoa học: "Robust Machine Translation Evaluation with Entailment Features∗" pptx
Ngày tải lên :
20/02/2014, 07:20
... machine translation. In Proceedings of
ACL, pages 160–167, Sapporo, Japan.
Karolina Owczarzak, Josef van Genabith, and Andy
Way. 2008. Evaluating machine translation with
LFG dependencies. Machine Translation, ... into a
more robust ensemble metric with linear regression.
Our second, more fundamental, strategy replaces
the use of loose surrogates of translation quality
with a model that attempts to comprehensively ... met-
rics treat any divergence from the reference as a
negative, while (computational) linguistics has long
dealt with linguistic variation that preserves the
meaning, usually called paraphrase, such...
- 9
- 467
- 0
Tài liệu Báo cáo khoa học: "Automatic learning of textual entailments with cross-pair similarities" ppt
Ngày tải lên :
20/02/2014, 12:20
... rows report the
cross-pair similarity carried out with Eq. 6 with
(Synt Trees with placeholders) and without (Only
Synt Trees) augmenting the trees with placehold-
ers, respectively. Each column ... Computational Linguistics and 44th Annual Meeting of the ACL, pages 401–408,
Sydney, July 2006.
c
2006 Association for Computational Linguistics
Automatic learning of textual entailments with cross-pair ... as a baseline approach or in combination with
the cross-pair similarity. This latter will be imple-
mented with tree kernel functions over syntactic
structures (Sec. 4.2).
4.1 Anchoring and Lexical...
- 8
- 413
- 0
Tài liệu Báo cáo khoa học: "Resolving Translation Mismatches With Information Flow" pdf
Ngày tải lên :
20/02/2014, 21:20
... Fea-
ture Structure Rewriting System with Inheritance. In Pro-
ceedings of the ~Tth Annual Meeting of the Association for
Computational Linguistics, Vancouver, Canada.
200
Resolving Translation ... motivate our ap-
proach with examples of translation between En-
glish and Japanese.
1
Introduction
The focus of machine translation (MT) technol-
ogy has been on the translation of sentence ...
Figure 5: The IFG for NP Translation
in an actual implementation.
5 A
translation example
We will now illustrate the proposed approach with
a Japanese-to-English translation example: the...
- 8
- 405
- 0
Báo cáo khoa học: "Training Phrase Translation Models with Leaving-One-Out" ppt
Ngày tải lên :
07/03/2014, 22:20
... β
(|
˜
f|+|˜e|)
with the source and target
Table 1: Avg. source phrase lengths in forced
alignment without leaving-one-out and with stan-
dard and length-based leaving-one-out.
avg. phrase length
without ... Association for Computational Linguistics, pages 475–484,
Uppsala, Sweden, 11-16 July 2010.
c
2010 Association for Computational Linguistics
Training Phrase Translation Models with Leaving-One-Out
Joern ... can
improve translation performance on a state-of-
the-art phrase-based translation model. This is
achieved by training phrase translation probabil-
ities in a way that they are consistent with their
use...
- 10
- 391
- 0
Báo cáo khoa học: "Consistent Translation using Discriminative Learning: A Translation Memory-inspired Approach" pdf
Ngày tải lên :
07/03/2014, 22:20
... statistical machine translation with translation
memory output through tree-based structural align-
ment. In Proceedings of the Fourth Workshop on Syn-
tax and Structure in Statistical Translation, ... Computational Linguistics, pages 1239–1248,
Portland, Oregon, June 19-24, 2011.
c
2011 Association for Computational Linguistics
Consistent Translation using Discriminative Learning:
A Translation ... guarantee
the usefulness of a particular translation. We address
this problem using discriminative learning.
3 Constrained Translation with
Discriminative Learning
3.1 Formulation of the Problem
Given...
- 10
- 305
- 0
Báo cáo khoa học: "HUMAN INTENTION-BASED SEGMENTATION: RELIABILITY AND CORRELATION WITH LINGUISTIC CUES" doc
Ngày tải lên :
08/03/2014, 07:20
... grouped into two hierarchically structured seg-
ments, with segment 2 embedded in segment 1. This
segmental structure is crucial for determining that
the boxed pronoun he corefers with the boxed ... of discourse
segmentation with three linguistic cues: referential
noun phrases, cue words, and pauses.
Figure 1 illustrates how discourse structure in-
teracts with reference resolution in ... linguistic cues with dis-
course structure. By asking subjects to segment
discourse using a non -linguistic criterion, the corre-
lation of linguistic devices with independently de-
rived segments...
- 8
- 224
- 0
Báo cáo khoa học: "Computing Term Translation Probabilities with Generalized Latent Semantic Analysis" pptx
Ngày tải lên :
08/03/2014, 21:20
... to
model the term translation probabilities. We used
a simple k-NN classifier and a basic baseline to
evalute the performance. We used the GLSA-
based term translation probabilities within the lan-
guage ... information which helps to go
beyond term matching and deal with synonymy
and polysemy.
4 Conclusion and Future Work
We used the GLSA to compute term translation
probabilities as a measure of semantic ... in
Computer Science, 2167:491–502.
154
our preliminary experiments, the GLSA with PMI
showed a better performance than with other co-
occurrence based measures such as the likelihood
ratio, and...
- 4
- 323
- 0
Báo cáo khoa học: "A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model" pot
Ngày tải lên :
17/03/2014, 02:20
... category. For example, we can unify a
fixed structure with a floating structure or two float-
ing structures in the same direction, but we cannot
unify two fixed structures.
h
1
h
2
=
h
1
if h
2
= ... combined via concate-
nation. We can concatenate two fixed structures, one
fixed structure with one floating structure, or two
floating structures in the same direction. The flex-
ibility of the order ... of
dependency structures and constrain operations in
decoding. For example, we have a rule with depen-
dency structure f ind ← X, where X right adjoins
to find. Suppose we have two floating structures
2
,
cat(X
1
)...
- 9
- 442
- 0
Báo cáo khoa học: "Semantic Class Learning from the Web with Hyponym Pattern Linkage Graphs" pdf
Ngày tải lên :
17/03/2014, 02:20
... super-
vised semantic class learning from the web,
using a single powerful hyponym pattern com-
bined with graph structures, which capture
two properties associated with pattern-based
extractions: ... 1048–1056,
Columbus, Ohio, USA, June 2008.
c
2008 Association for Computational Linguistics
Semantic Class Learning from the Web with Hyponym Pattern Linkage
Graphs
Zornitsa Kozareva
DLSI, University ... semantic class learning, under a variety
of different names and with a variety of different
goals. Given the great deal of similar work in infor-
mation extraction and ontology learning, we focus
here...
- 9
- 340
- 0
Báo cáo khoa học: "Unsupervised Learning of Dependency Structure for Language Modeling" potx
Ngày tải lên :
17/03/2014, 06:20
...
built with and without PW. In Table 2, the PW-
prefix refers to the DLMs with PW = 0.5, and the
DLMs without PW- prefix refers to DLMs with PW
= 0. For both DLM_1 and DLM_2, models with the ... de-
pendency structure into an n-gram language
model to capture long distance word de-
pendency. Second, we present an unsuper-
vised learning method that discovers the
dependency structure of ... to estimate; (2)
capturing deeper linguistic relations in a language
model requires a large annotated training corpus
and a decoder that assigns linguistic structure,
which are not always available....
- 8
- 380
- 0
Báo cáo khoa học: "SEMANTIC STRUCTURE WITH ANALYSIS ADNOMINAL OF JAPANESE PARTICLES NOUN PHRASES" pot
Ngày tải lên :
17/03/2014, 20:20
... correct structure can be obtained by
unifying an event semantic structure with a predicate
feature in
A no B
as follows.
event-semantic -structure- in-context
-
pred -structure- in-semantic -structure- of-A ... predicate structure in A no B semantic
structure and the related event structure in the
discourse. A sequence of related events is described in
a discourse. On the other hand, the semantic structure ...
sense:
pred:
np
animate
(sense)
Semantic structure of
gruupu
("group"]
125
SEMANTIC STRUCTURE ANALYSIS OF JAPANESE NOUN PHRASES
WITH ADNOMINAL PARTICLES
Akira SHIMAZU, Shozo...
- 8
- 344
- 0