1 |
DeepL et Google Translate face à l'ambiguïté phraséologique
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03583995 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
2 |
VEREINDEUTIGUNG ZUR KLASSIFIZIERUNG LEXIKALISCHER OBJEKTE ; DISAMBIGUATION FOR THE CLASSIFICATION OF LEXICAL ITEMS ; DÉSAMBÏGUISATION POUR LA CLASSIFICATION DE LEXÈMES
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03598242 ; France, Patent n° : EP3937059A1. 2022 (2022)
|
|
BASE
|
|
Show details
|
|
3 |
A New Amharic Speech Emotion Dataset and Classification Benchmark ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
LPC Augment: An LPC-Based ASR Data Augmentation Algorithm for Low and Zero-Resource Children's Dialects ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Automatic Dialect Density Estimation for African American English ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Multi-View Spatial-Temporal Network for Continuous Sign Language Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Exploring Sub-skeleton Trajectories for Interpretable Recognition of Sign Language ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Improving Persian Relation Extraction Models by Data Augmentation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Russian SuperGLUE 1.1: Revising the Lessons not Learned by Russian NLP models ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval ...
|
|
|
|
Abstract:
State-of-the-art neural (re)rankers are notoriously data hungry which - given the lack of large-scale training data in languages other than English - makes them rarely used in multilingual and cross-lingual retrieval settings. Current approaches therefore typically transfer rankers trained on English data to other languages and cross-lingual setups by means of multilingual encoders: they fine-tune all the parameters of a pretrained massively multilingual Transformer (MMT, e.g., multilingual BERT) on English relevance judgments and then deploy it in the target language. In this work, we show that two parameter-efficient approaches to cross-lingual transfer, namely Sparse Fine-Tuning Masks (SFTMs) and Adapters, allow for a more lightweight and more effective zero-shot transfer to multilingual and cross-lingual retrieval tasks. We first train language adapters (or SFTMs) via Masked Language Modelling and then train retrieval (i.e., reranking) adapters (SFTMs) on top while keeping all other parameters fixed. At ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; H.3.3; I.2.7; Information Retrieval cs.IR
|
|
URL: https://dx.doi.org/10.48550/arxiv.2204.02292 https://arxiv.org/abs/2204.02292
|
|
BASE
|
|
Hide details
|
|
13 |
Politics and Virality in the Time of Twitter: A Large-Scale Cross-Party Sentiment Analysis in Greece, Spain and United Kingdom ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Tackling data scarcity in speech translation using zero-shot multilingual machine translation techniques ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
A new approach to calculating BERTScore for automatic assessment of translation quality ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Emergent Communication for Understanding Human Language Evolution: What's Missing? ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
A Feasibility Study of Answer-Agnostic Question Generation for Education ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Computational historical linguistics and language diversity in South Asia ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|