Home
Catalogue search
Refine your search:
Keyword
Creator / Publisher:
Ren, Xiang (8)
The 2021 Conference on Empirical Methods in Natural Language Processing 2021 (8)
Lin, Yuchen (3)
Pujara, Jay (2)
Zhou, Pei (2)
Galstyan, Aram (1)
Gao, Wenyang (1)
Gheini, Mozhdeh (1)
Han, Jiawei (1)
Han, Rujun (1)
more
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 – 8 of 8
1
Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Gheini, Mozhdeh
;
May, Jonathan
;
Ren, Xiang
. - : Underline Science Inc., 2021
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.132/ Abstract: We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series of experiments through fine-tuning a translation model on data where either the source or target language has changed. These experiments reveal that fine-tuning only the cross-attention parameters is nearly as effective as fine-tuning all parameters (i.e., the entire translation model). We provide insights into why this is the case and observe that limiting fine-tuning in this manner yields cross-lingually aligned embeddings. The implications of this finding for researchers and practitioners include a mitigation of catastrophic forgetting, the potential for zero-shot translation, and the ability to extend machine translation models to several new language pairs with reduced parameter storage ...
Keyword:
Computational Linguistics
;
Machine Learning
;
Machine Learning and Data Mining
;
Machine translation
;
Natural Language Processing
URL:
https://dx.doi.org/10.48448/pgv2-cn55
https://underline.io/lecture/37970-cross-attention-is-all-you-need-adapting-pretrained-transformers-for-machine-translation
BASE
Hide details
2
RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Ho, Daniel
;
Khanna, Rahul
. - : Underline Science Inc., 2021
BASE
Show details
3
Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Jin, Xisen
;
Lin, Yuchen
. - : Underline Science Inc., 2021
BASE
Show details
4
RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Gao, Wenyang
;
Lin, Yuchen
. - : Underline Science Inc., 2021
BASE
Show details
5
ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Han, Rujun
;
Peng, Nanyun
. - : Underline Science Inc., 2021
BASE
Show details
6
Discretized Integrated Gradients for Explaining Language Models ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Ren, Xiang
;
Sanyal, Soumya
. - : Underline Science Inc., 2021
BASE
Show details
7
Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Galstyan, Aram
;
Mehrabi, Ninareh
. - : Underline Science Inc., 2021
BASE
Show details
8
Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Han, Jiawei
;
Mao, Yuning
. - : Underline Science Inc., 2021
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
8
Linguistik-Repository
0
IDS Publikationsserver
0
Online dissertations
0
Language Description Heritage
0
© 2013 - 2024 Lin|gu|is|tik
|
Imprint
|
Privacy Policy
|
Datenschutzeinstellungen ändern