1 |
Towards Best Practices for Training Multilingual Dense Retrieval Models ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Linguistic metaconcepts can improve grammatical understanding in L1 education evidence from a Dutch quasi-experimental study
|
|
|
|
In: PLoS One (2022)
|
|
BASE
|
|
Show details
|
|
6 |
Note d’onomastique édessénienne
|
|
|
|
In: Le calame et le ciseau. Colophons syriaques offerts à Françoise Briquel Chatonnet ; https://halshs.archives-ouvertes.fr/halshs-03465987 ; Brelaud Simon; Daccache Jimmy; Debié Muriel; Farina Margherita; Ruani Flavia; Villey Émilie. Le calame et le ciseau. Colophons syriaques offerts à Françoise Briquel Chatonnet, 8, Geuthner, pp.57-68, 2021, Cahiers d’Études syriaques, 978-2-7053-4091-9 (2021)
|
|
BASE
|
|
Show details
|
|
7 |
Les textes linguistiques de David bar Paulos
|
|
|
|
In: Le calame et le ciseau. Colophons syriaques offerts à Françoise Briquel Chatonnet ; https://hal.archives-ouvertes.fr/hal-03462526 ; Brelaud, Simon; Daccache, Jimmy; Farina, Margherita; Debié, Muriel; Ruani, Flavia; Villey, Emilie. Le calame et le ciseau. Colophons syriaques offerts à Françoise Briquel Chatonnet, Le calame et le ciseau. Colophons syriaques offerts à Françoise Briquel Chatonnet (8), Geuthner, 2021, Cahiers d'études syriaques, 9782705340919 ; https://geuthner.com (2021)
|
|
BASE
|
|
Show details
|
|
8 |
« La nasalisation dans le nord-occitan de la Drôme »
|
|
|
|
In: 5ème édition du Colloque International Langue et Territoire. U. Paul-Valéry de Montpellier. https://let2021.sciencesconf.org/ ; https://hal.archives-ouvertes.fr/hal-03195340 ; 5ème édition du Colloque International Langue et Territoire. U. Paul-Valéry de Montpellier. https://let2021.sciencesconf.org/, Jun 2021, Montpellier, France (2021)
|
|
BASE
|
|
Show details
|
|
9 |
Understanding grammar: the impact of linguistic metaconcepts on L1 grammar education ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Domain Adaptation with Pre-trained Transformers for Query Focused Abstractive Text Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Exploring Listwise Evidence Reasoning with T5 for Fact Verification ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Contextualized Query Embeddings for Conversational Search ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing ...
|
|
|
|
Abstract:
Read paper: https://www.aclanthology.org/2021.acl-long.84 Abstract: In selective prediction, a classifier is allowed to abstain from making predictions on low-confidence examples. Though this setting is interesting and important, selective prediction has rarely been examined in natural language processing (NLP) tasks. To fill this void in the literature, we study in this paper selective prediction for NLP, comparing different models and confidence estimators. We further propose a simple error regularization trick that improves confidence estimation without substantially increasing the computation budget. We show that recent pre-trained transformer models simultaneously improve both model accuracy and confidence estimation effectiveness. We also find that our proposed regularization improves confidence estimation and can be applied to other relevant scenarios, such as using classifier cascades for accuracy--efficiency trade-offs. Source code for this paper can be found at ...
|
|
URL: https://underline.io/lecture/25966-the-art-of-abstention-selective-prediction-and-error-regularization-for-natural-language-processing https://dx.doi.org/10.48448/9jnz-7f73
|
|
BASE
|
|
Hide details
|
|
16 |
Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Sparsifying Sparse Representations for Passage Retrieval by Top-$k$ Masking ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
About ancient altars (ne tuye) ; Les autels magiques (ne tuye)
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Village council about marriage ; Conseil de village à propos du mariage
|
|
In: ED11-08 (2021)
|
|
BASE
|
|
Show details
|
|
20 |
Unsupervised Chunking as Syntactic Structure Induction with a Knowledge-Transfer Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|