1 |
Multilingual Unsupervised Sentence Simplification
|
|
|
|
In: https://hal.inria.fr/hal-03109299 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Text Generation with and without Retrieval ; Génération de textes basés sur la connaissance avec et sans recherche
|
|
|
|
In: https://hal.univ-lorraine.fr/tel-03542634 ; Computer Science [cs]. Université de Lorraine, 2021. English. ⟨NNT : 2021LORR0164⟩ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Findings of the AmericasNLP 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Alternative Input Signals Ease Transfer in Multilingual Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Multilingual AMR-to-Text Generation
|
|
|
|
In: 2020 Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-02999676 ; 2020 Conference on Empirical Methods in Natural Language Processing, Nov 2020, Punta Cana, Dominican Republic (2020)
|
|
Abstract:
International audience ; Generating text from structured data is challenging because it requires bridging the gap between (i) structure and natural language (NL) and (ii) semantically underspecified input and fully specified NL output. Multilingual generation brings in an additional challenge: that of generating into languages with varied word order and morphological properties. In this work, we focus on Abstract Meaning Representations (AMRs) as structured input, where previous research has overwhelmingly focused on generating only into English. We leverage advances in cross-lingual embeddings, pretraining, and multilingual models to create multilingual AMR-to-text models that generate in twenty one different languages. For eighteen languages, based on automatic metrics, our multilingual models surpass baselines that generate into a single language. We analyse the ability of our multilingual models to accurately capture morphology and word order using human evaluation, and find that native speakers judge our generations to be fluent.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
|
|
URL: https://hal.archives-ouvertes.fr/hal-02999676/document https://hal.archives-ouvertes.fr/hal-02999676/file/amr_to_text_generation__camera_ready_%20%282%29.pdf https://hal.archives-ouvertes.fr/hal-02999676
|
|
BASE
|
|
Hide details
|
|
10 |
Augmenting Transformers with KNN-Based Composite Memory for Dialog
|
|
|
|
In: EISSN: 2307-387X ; Transactions of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-02999678 ; Transactions of the Association for Computational Linguistics, The MIT Press, In press, ⟨10.1162/tacl_a_00356⟩ ; https://transacl.org/index.php/tacl (2020)
|
|
BASE
|
|
Show details
|
|
11 |
Multilingual Translation with Extensible Multilingual Pretraining and Finetuning ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Beyond English-Centric Multilingual Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|