Home
Catalogue search
Refine your search:
Keyword
Creator / Publisher:
Koehn, Philipp (61)
Haddow, Barry (7)
Knight, Kevin (5)
Koehn, Philipp [Verfasser] (5)
Saint-Amand, Herve (5)
Buck, Christian (4)
Engineering and Physical Sciences Research Council (EPSRC) (4)
Germann, Ulrich (4)
Osborne, Miles (4)
Alabau, Vicent (3)
more
Year
Medium:
Online (43)
Print (23)
Type:
Article (32)
Book (18)
Miscellaneous (13)
Website (2)
Journal (1)
BLLDB-Access
Search in the Catalogues and Directories
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
Sort by
creator [A → Z]
'
creator [Z → A]
'
publishing year ↑ (asc)
'
publishing year ↓ (desc)
'
title [A → Z]
'
title [Z → A]
'
Simple Search
Page:
1
2
3
4
Hits 1 – 20 of 66
1
Pushing the right buttons: adversarial evaluation of quality estimation
Specia, Lucia
;
Fomicheva, Marina
;
Ranasinghe, Tharindu
...
In: Proceedings of the Sixth Conference on Machine Translation ; 625 ; 638 (2022)
BASE
Show details
2
Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
., Sanjeev
;
Koehn, Philipp
;
Kumar, Gaurav
. - : Underline Science Inc., 2021
Abstract:
Large web-crawled corpora represent an excellent resource for improving the performance of Neural Machine Translation (NMT) systems across several language pairs. However, since these corpora are typically extremely noisy, their use is fairly limited. Current approaches to deal with this problem mainly focus on filtering using heuristics or single features such as language model scores or bi-lingual similarity. This work presents an alternative approach which learns weights for multiple sentence-level features. These feature weights which are optimized directly for the task of improving translation performance, are used to score and filter sentences in the noisy corpora more effectively. We provide results of applying this technique to building NMT systems using the Paracrawl corpus for Estonian-English and show that it beats strong single feature baselines and hand designed combinations. Additionally, we analyze the sensitivity of this method to different types of noise and explore if the learned weights ...
URL:
https://underline.io/lecture/39478-learning-feature-weights-using-reward-modeling-for-denoising-parallel-corpora
https://dx.doi.org/10.48448/xmmn-vb09
BASE
Hide details
3
Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora ...
Kumar, Gaurav
;
Koehn, Philipp
;
Khudanpur, Sanjeev
. - : arXiv, 2021
BASE
Show details
4
Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions ...
Xu, Haoran
;
Koehn, Philipp
. - : arXiv, 2021
BASE
Show details
5
Learning Policies for Multilingual Training of Neural Machine Translation Systems ...
Kumar, Gaurav
;
Koehn, Philipp
;
Khudanpur, Sanjeev
. - : arXiv, 2021
BASE
Show details
6
Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation ...
Xu, Haoran
;
Koehn, Philipp
. - : arXiv, 2021
BASE
Show details
7
Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry ...
Marchisio, Kelly
;
Xiong, Conghao
;
Koehn, Philipp
. - : arXiv, 2021
BASE
Show details
8
Facebook AI WMT21 News Translation Task Submission ...
Tran, Chau
;
Bhosale, Shruti
;
Cross, James
. - : arXiv, 2021
BASE
Show details
9
Levenshtein Training for Word-level Quality Estimation ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
., Matt
;
Ding, Shuoyang
. - : Underline Science Inc., 2021
BASE
Show details
10
Alternative Input Signals Ease Transfer in Multilingual Machine Translation ...
Sun, Simeng
;
Fan, Angela
;
Cross, James
. - : arXiv, 2021
BASE
Show details
11
An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces ...
Marchisio, Kelly
;
Park, Youngser
;
Saad-Eldin, Ali
. - : arXiv, 2021
BASE
Show details
12
XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment ...
El-Kishky, Ahmed
;
Renduchintala, Adithya
;
Cross, James
. - : arXiv, 2021
BASE
Show details
13
Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data ...
Ko, Wei-Jen
;
El-Kishky, Ahmed
;
Renduchintala, Adithya
. - : arXiv, 2021
BASE
Show details
14
An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
., Ali
;
Alyakin, Anyon
. - : Underline Science Inc., 2021
BASE
Show details
15
Neural machine translation
Koehn, Philipp
. - Cambridge : Cambridge University Press, 2020
BLLDB
UB Frankfurt Linguistik
Show details
16
Exploiting Sentence Order in Document Alignment ...
Thompson, Brian
;
Koehn, Philipp
. - : arXiv, 2020
BASE
Show details
17
A user study of neural interactive translation prediction [<Journal>]
Knowles, Rebecca
[Verfasser];
Sanchez-Torron, Marina
[Verfasser];
Koehn, Philipp
[Verfasser]
DNB Subject Category Language
Show details
18
Findings of the 2018 conference on machine translation (WMT18)
Federmann, Christian
;
Koehn, Philipp
;
Monz, Christof
...
In: Bojar, Ondřej orcid:0000-0002-0606-0050 , Federmann, Christian, Fishel, Mark, Graham, Yvette, Haddow, Barry, Huck, Matthias, Koehn, Philipp and Monz, Christof (2018) Findings of the 2018 conference on machine translation (WMT18). In: Third Conference on Machine Translation, Volume 2: Shared Task Papers, 31 Oct - 1 Nov 2018, Brussels, Belgium. (2018)
BASE
Show details
19
ParaCrawl Corpus version 1.0
Koehn, Philipp
;
Heafield, Kenneth
;
Forcada, Mikel L.
. - : ParaCrawl, 2018
BASE
Show details
20
On the Impact of Various Types of Noise on Neural Machine Translation ...
Khayrallah, Huda
;
Koehn, Philipp
. - : arXiv, 2018
BASE
Show details
Page:
1
2
3
4
Mobile view
All
Catalogues
UB Frankfurt Linguistik
2
IDS Mannheim
1
OLC Linguistik
11
UB Frankfurt Retrokatalog
0
DNB Subject Category Language
5
Institut für Empirische Sprachwissenschaft
0
Leibniz-Centre General Linguistics (ZAS)
0
Bibliographies
BLLDB
14
BDSL
0
IDS Bibliografie zur deutschen Grammatik
0
IDS Bibliografie zur Gesprächsforschung
0
IDS Konnektoren im Deutschen
0
IDS Präpositionen im Deutschen
0
IDS OBELEX meta
0
MPI-SHH Linguistics Collection
0
MPI for Psycholinguistics
0
Linked Open Data catalogues
Annohub
0
Online resources
Link directory
2
Journal directory
0
Database directory
0
Dictionary directory
0
Open access documents
BASE
41
Linguistik-Repository
0
IDS Publikationsserver
0
Online dissertations
0
Language Description Heritage
0
© 2013 - 2024 Lin|gu|is|tik
|
Imprint
|
Privacy Policy
|
Datenschutzeinstellungen ändern