1 |
Observation of new excited ${B} ^0_{s} $ states
|
|
|
|
In: Eur.Phys.J.C ; https://hal.archives-ouvertes.fr/hal-03010999 ; Eur.Phys.J.C, 2021, 81 (7), pp.601. ⟨10.1140/epjc/s10052-021-09305-3⟩ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
End-to-end Speech Translation via Cross-modal Progressive Training ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Locate then Segment: A Strong Pipeline for Referring Image Segmentation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Learning Language Specific Sub-network for Multilingual Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Contrastive Learning for Many-to-many Multilingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Multilingual Translation via Grafting Pre-trained Language Models ...
|
|
|
|
Abstract:
Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However, directly connecting BERT as an encoder and GPT as a decoder can be challenging in machine translation, for GPT-like models lack a cross-attention component that is needed in seq2seq decoders. In this paper, we propose Graformer to graft separately pre-trained (masked) language models for machine translation. With monolingual data for pre-training and parallel data for grafting training, we maximally take advantage of the usage of both types of data. Experiments on 60 directions show that our method achieves average improvements of 5.8 BLEU in x2en and 2.9 BLEU in en2x directions comparing with the multilingual Transformer of the same size. ... : Accepted in EMNLP 2021 (Findings) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2109.05256 https://dx.doi.org/10.48550/arxiv.2109.05256
|
|
BASE
|
|
Hide details
|
|
9 |
Counter-Interference Adapter for Multilingual Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
MTG: A Benchmarking Suite for Multilingual Text Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Language Tags Matter for Zero-Shot Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Personalized Transformer for Explainable Recommendation ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Dynamic Knowledge Distillation for Pre-trained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Learning Shared Semantic Space for Speech-to-Text Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Glancing Transformer for Non-Autoregressive Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Probabilistic Graph Reasoning for Natural Proof Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Multilingual Translation via Grafting Pre-trained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Language Tags Matter for Zero-Shot Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|