1 |
Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles
|
|
|
|
In: CtrlGen: Controllable Generative Modeling in Language and Vision ; https://hal.inria.fr/hal-03540084 ; CtrlGen: Controllable Generative Modeling in Language and Vision, Jan 2022, virtual, France (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
|
|
|
|
In: Seventh Workshop on Noisy User-generated Text (W-NUT 2021, colocated with EMNLP 2021) ; https://hal.inria.fr/hal-03527328 ; Seventh Workshop on Noisy User-generated Text (W-NUT 2021, colocated with EMNLP 2021), Jan 2022, punta cana, Dominican Republic ; https://aclanthology.org/2021.wnut-1.47/ (2022)
|
|
BASE
|
|
Show details
|
|
3 |
First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT
|
|
|
|
In: https://hal.inria.fr/hal-03161685 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Can Multilingual Language Models Transfer to an Unseen Dialect? A Case Study on North African Arabizi
|
|
|
|
In: https://hal.inria.fr/hal-03161677 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
5 |
First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT
|
|
|
|
In: EACL 2021 - The 16th Conference of the European Chapter of the Association for Computational Linguistics ; https://hal.inria.fr/hal-03239087 ; EACL 2021 - The 16th Conference of the European Chapter of the Association for Computational Linguistics, Apr 2021, Kyiv / Virtual, Ukraine ; https://2021.eacl.org/ (2021)
|
|
BASE
|
|
Show details
|
|
6 |
When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models
|
|
|
|
In: NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies ; https://hal.inria.fr/hal-03251105 ; NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2021, Mexico City, Mexico (2021)
|
|
BASE
|
|
Show details
|
|
7 |
PAGnol: An Extra-Large French Generative Model
|
|
|
|
In: https://hal.inria.fr/hal-03540159 ; [Research Report] LightON. 2021 (2021)
|
|
BASE
|
|
Show details
|
|
8 |
Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering
|
|
|
|
In: https://hal.inria.fr/hal-03109187 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
9 |
Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models
|
|
|
|
In: W-NUT 2021 - 7th Workshop on Noisy User-generated Text (colocated with EMNLP 2021) ; https://hal.inria.fr/hal-03540174 ; W-NUT 2021 - 7th Workshop on Noisy User-generated Text (colocated with EMNLP 2021), Association for computational linguistics, Nov 2021, Punta Cana, Dominican Republic (2021)
|
|
BASE
|
|
Show details
|
|
10 |
Understanding the Impact of UGC Specificities on Translation Quality
|
|
|
|
In: W-NUT 2021 - Seventh Workshop on Noisy User-generated Text (colocated with EMNLP 2021) ; https://hal.inria.fr/hal-03540175 ; W-NUT 2021 - Seventh Workshop on Noisy User-generated Text (colocated with EMNLP 2021), association for computational linguistics, Nov 2021, Punta Cana, Dominican Republic (2021)
|
|
BASE
|
|
Show details
|
|
11 |
Challenging the Semi-Supervised VAE Framework for Text Classification
|
|
|
|
In: Second Workshop on Insights from Negative Results in NLP (colocated with EMNLP) ; https://hal.inria.fr/hal-03540081 ; Second Workshop on Insights from Negative Results in NLP (colocated with EMNLP), Nov 2021, Punta Cana, Dominican Republic ; https://insights-workshop.github.io/2021/ (2021)
|
|
BASE
|
|
Show details
|
|
17 |
Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios? ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT ...
|
|
|
|
Abstract:
Multilingual pretrained language models have demonstrated remarkable zero-shot cross-lingual transfer capabilities. Such transfer emerges by fine-tuning on a task of interest in one language and evaluating on a distinct language, not seen during the fine-tuning. Despite promising results, we still lack a proper understanding of the source of this transfer. Using a novel layer ablation technique and analyses of the model's internal representations, we show that multilingual BERT, a popular multilingual language model, can be viewed as the stacking of two sub-networks: a multilingual encoder followed by a task-specific language-agnostic predictor. While the encoder is crucial for cross-lingual transfer and remains mostly unchanged during fine-tuning, the task predictor has little importance on the transfer and can be reinitialized during fine-tuning. We present extensive experiments with three distinct tasks, seventeen typologically diverse languages and multiple domains to support our hypothesis. ... : Accepted at EACL 2021 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2101.11109 https://dx.doi.org/10.48550/arxiv.2101.11109
|
|
BASE
|
|
Hide details
|
|
19 |
Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|