Page: 1 2 3 4 5 6 7... 150
42 |
A Neural Pairwise Ranking Model for Readability Assessment ...
|
|
|
|
BASE
|
|
Show details
|
|
43 |
SMDT: Selective Memory-Augmented Neural Document Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
44 |
CausalKG: Causal Knowledge Graph Explainability using interventional and counterfactual reasoning ...
|
|
|
|
BASE
|
|
Show details
|
|
45 |
Learn from Structural Scope: Improving Aspect-Level Sentiment Analysis with Hybrid Graph Convolutional Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
46 |
Learning the Ordering of Coordinate Compounds and Elaborate Expressions in Hmong, Lahu, and Chinese ...
|
|
|
|
BASE
|
|
Show details
|
|
47 |
Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition ...
|
|
|
|
BASE
|
|
Show details
|
|
48 |
Modeling Intensification for Sign Language Generation: A Computational Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
49 |
A Transformer-Based Contrastive Learning Approach for Few-Shot Sign Language Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
50 |
Open Source HamNoSys Parser for Multilingual Sign Language Encoding ...
|
|
|
|
BASE
|
|
Show details
|
|
51 |
A Comprehensive Review of Sign Language Recognition: Different Types, Modalities, and Datasets ...
|
|
|
|
BASE
|
|
Show details
|
|
52 |
Sign Language Video Retrieval with Free-Form Textual Queries ...
|
|
|
|
BASE
|
|
Show details
|
|
53 |
Sign Language Recognition System using TensorFlow Object Detection API ...
|
|
|
|
BASE
|
|
Show details
|
|
54 |
pNLP-Mixer: an Efficient all-MLP Architecture for Language ...
|
|
|
|
BASE
|
|
Show details
|
|
56 |
Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments ...
|
|
|
|
BASE
|
|
Show details
|
|
57 |
Cross-Lingual Text-to-Speech Using Multi-Task Learning and Speaker Classifier Joint Training ...
|
|
|
|
BASE
|
|
Show details
|
|
58 |
Focus on the Target's Vocabulary: Masked Label Smoothing for Machine Translation ...
|
|
|
|
Abstract:
Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that simply applying both techniques can be conflicting and even leads to sub-optimal performance. When allocating smoothed probability, original label smoothing treats the source-side words that would never appear in the target language equally to the real target-side words, which could bias the translation model. To address this issue, we propose Masked Label Smoothing (MLS), a new mechanism that masks the soft label probability of source-side words to zero. Simple yet effective, MLS manages to better integrate label smoothing with vocabulary sharing. Our extensive experiments show that MLS consistently yields improvement over original label smoothing on different datasets, including bilingual and multilingual translation from both translation quality and model's calibration. Our code is released at https://github.com/PKUnlp-icler/MLS ... : ACL 2022 Main Conference, released at https://github.com/PKUnlp-icler/MLS ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2203.02889 https://dx.doi.org/10.48550/arxiv.2203.02889
|
|
BASE
|
|
Hide details
|
|
59 |
Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information ...
|
|
|
|
BASE
|
|
Show details
|
|
60 |
Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7... 150
|
|