2 |
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models? ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
The Power of Scale for Parameter-Efficient Prompt Tuning ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
mT5: A massively multilingual pre-trained text-to-text transformer ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Towards Zero-Shot Multilingual Synthetic Question and Answer Generation for Cross-Lingual Reading Comprehension ...
|
|
|
|
Abstract:
We propose a simple method to generate multilingual question and answer pairs on a large scale through the use of a single generative model. These synthetic samples can be used to improve the zero-shot performance of multilingual QA models on target languages. Our proposed multi-task training of the generative model only requires the labeled training samples in English, thus removing the need for such samples in the target languages, making it applicable to far more languages than those with labeled data. Human evaluations indicate the majority of such samples are grammatically correct and sensible. Experimental results show our proposed approach can achieve large gains on the XQuAD dataset, reducing the gap between zero-shot and supervised performance of smaller QA models on various languages. ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://arxiv.org/abs/2010.12008 https://dx.doi.org/10.48550/arxiv.2010.12008
|
|
BASE
|
|
Hide details
|
|
11 |
LAReQA: Language-agnostic answer retrieval from a multilingual pool ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Multilingual Universal Sentence Encoder for Semantic Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Effective Parallel Corpus Mining using Bilingual Sentence Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Contrastive Topic: Meanings and Realizations
|
|
|
|
In: Doctoral Dissertations (2014)
|
|
BASE
|
|
Show details
|
|
17 |
Witnessable quantifiers license type-e meaning: Evidence from contrastive topic, equatives and supplements
|
|
|
|
In: Semantics and Linguistic Theory; Proceedings of SALT 22; 286-306 ; 2163-5951 (2012)
|
|
BASE
|
|
Show details
|
|
18 |
Mandarin 'even', `all' and the Trigger of Focus Movement
|
|
|
|
In: University of Pennsylvania Working Papers in Linguistics (2010)
|
|
BASE
|
|
Show details
|
|
|
|