Home
Catalogue search
Refine your search:
Keyword:
Artificial Intelligence cs.AI (2)
Computation and Language cs.CL (2)
FOS Computer and information sciences (2)
Machine Learning cs.LG (2)
Computer and Information Science (1)
Information Retrieval cs.IR (1)
Natural Language Processing (1)
Neural Network (1)
Creator / Publisher:
Korhonen, Anna (5)
Li, Yaoyiran (5)
Ponti, Edoardo (3)
Vulić, Ivan (3)
Vulic, Ivan (2)
Collier, Nigel (1)
Liu, Fangyu (1)
Ponti, Edoardo M. (1)
The 28th International Conference on Computational Linguistics 2020 (1)
Year
Medium
Type
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
Hits 1 – 5 of 5
1
Improving Word Translation via Two-Stage Contrastive Learning ...
Li, Yaoyiran
;
Liu, Fangyu
;
Collier, Nigel
. - : arXiv, 2022
BASE
Show details
2
Emergent Communication Pretraining for Few-Shot Machine Translation ...
Li, Yaoyiran
;
Ponti, Edoardo M.
;
Vulić, Ivan
. - : arXiv, 2020
BASE
Show details
3
Emergent Communication Pretraining for Few-Shot Machine Translation ...
Li, Yaoyiran
;
Ponti, Edoardo
;
Vulic, Ivan
;
Korhonen, Anna
. - : Apollo - University of Cambridge Repository, 2020
Abstract:
While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world’s languages lack such resources. Hence, we investigate a more radical form of unsupervised knowledge transfer in the absence of linguistic data. In particular, for the first time we pretrain neural networks via emergent communication from referential games. Our key assumption is that grounding communication on images—as a crude approximation of real-world environments—inductively biases the model towards learning natural languages. On the one hand, we show that this substantially benefits machine translation in few-shot settings. On the other hand, this also provides an extrinsic evaluation protocol to probe the properties of emergent languages ex vitro. Intuitively, the closer they are to natural languages, the higher the gains from pretraining on them should be. For instance, in ...
URL:
https://www.repository.cam.ac.uk/handle/1810/315110
https://dx.doi.org/10.17863/cam.62217
BASE
Hide details
4
Emergent Communication Pretraining for Few-Shot Machine Translation ...
The 28th International Conference on Computational Linguistics 2020
;
Korhonen, Anna
;
Li, Yaoyiran
. - : Underline Science Inc., 2020
BASE
Show details
5
Emergent Communication Pretraining for Few-Shot Machine Translation
Vulic, Ivan
;
Ponti, Edoardo
;
Korhonen, Anna
. - : International Committee on Computational Linguistics, 2020. : https://www.aclweb.org/anthology/2020.coling-main.416, 2020. : Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), 2020
BASE
Show details
Mobile view
All
Catalogues
UB Frankfurt Linguistik
0
IDS Mannheim
0
OLC Linguistik
0
UB Frankfurt Retrokatalog
0
DNB Subject Category Language
0
Institut für Empirische Sprachwissenschaft
0
Leibniz-Centre General Linguistics (ZAS)
0
Bibliographies
BLLDB
0
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
0
Journal directory
0
Database directory
0
Dictionary directory
0
Open access documents
BASE
5
Linguistik-Repository
0
IDS Publikationsserver
0
Online dissertations
0
Language Description Heritage
0
© 2013 - 2024 Lin|gu|is|tik
|
Imprint
|
Privacy Policy
|
Datenschutzeinstellungen ändern