Page: 1 2 3 4 5 6 7 8... 842
61 |
Pirá: A Bilingual Portuguese-English Dataset for Question-Answering about the Ocean ...
|
|
|
|
BASE
|
|
Show details
|
|
62 |
A Neural Pairwise Ranking Model for Readability Assessment ...
|
|
|
|
BASE
|
|
Show details
|
|
63 |
A bilingual approach to specialised adjectives through word embeddings in the karstology domain ...
|
|
|
|
BASE
|
|
Show details
|
|
64 |
Universal Conditional Masked Language Pre-training for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
65 |
SMDT: Selective Memory-Augmented Neural Document Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
66 |
Learning How to Translate North Korean through South Korean ...
|
|
|
|
Abstract:
South and North Korea both use the Korean language. However, Korean NLP research has focused on South Korean only, and existing NLP systems of the Korean language, such as neural machine translation (NMT) models, cannot properly handle North Korean inputs. Training a model using North Korean data is the most straightforward approach to solving this problem, but there is insufficient data to train NMT models. In this study, we create data for North Korean NMT models using a comparable corpus. First, we manually create evaluation data for automatic alignment and machine translation. Then, we investigate automatic alignment methods suitable for North Korean. Finally, we verify that a model trained by North Korean bilingual data without human annotation can significantly boost North Korean translation accuracy compared to existing South Korean models in zero-shot settings. ... : 8 pages, 1 figures, 8 tables ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2201.11258 https://arxiv.org/abs/2201.11258
|
|
BASE
|
|
Hide details
|
|
67 |
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation? ...
|
|
|
|
BASE
|
|
Show details
|
|
68 |
Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
71 |
Speech Segmentation Optimization using Segmented Bilingual Speech Corpus for End-to-end Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
72 |
Examining the barriers to accessing and utilizing healthcare services for minority-language speakers with neurodevelopmental disorders: a scoping review ...
|
|
|
|
BASE
|
|
Show details
|
|
73 |
A New Amharic Speech Emotion Dataset and Classification Benchmark ...
|
|
|
|
BASE
|
|
Show details
|
|
74 |
Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks ...
|
|
|
|
BASE
|
|
Show details
|
|
76 |
Subspace-based Representation and Learning for Phonotactic Spoken Language Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
77 |
The Online Behaviour of the Algerian Abusers in Social Media Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
78 |
A Deep CNN Architecture with Novel Pooling Layer Applied to Two Sudanese Arabic Sentiment Datasets ...
|
|
|
|
BASE
|
|
Show details
|
|
79 |
Fine-Tuning Approach for Arabic Offensive Language Detection System: BERT-Based Model ...
|
|
|
|
BASE
|
|
Show details
|
|
80 |
Automatic Dialect Density Estimation for African American English ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8... 842
|
|