[HTML][HTML] A non-autoregressive Chinese-Braille translation approach with CTC loss optimization
Abstract The rise of Neural Machine Translation (NMT) models opens doors for translating
Chinese text into Braille, improving information access for visually impaired individuals …
Chinese text into Braille, improving information access for visually impaired individuals …
Pre-training model for low-resource Chinese–Braille translation
HL Yu, W Su, L Liu, J Zhang, C Cai, C Xu - Displays, 2023 - Elsevier
The technology for converting Chinese to Braille is of great importance. When paired with a
Braille display, it can better meet the educational and daily needs of the visually impaired …
Braille display, it can better meet the educational and daily needs of the visually impaired …
Automatic evaluation and analysis of idioms in neural machine translation
A major open problem in neural machine translation (NMT) is the translation of idiomatic
expressions, such as" under the weather". The meaning of these expressions is not …
expressions, such as" under the weather". The meaning of these expressions is not …
Improving Braille–Chinese translation with jointly trained and pre-trained language models
T Huang, W Su, L Liu, C Cai, H Yu, Y Yuan - Displays, 2024 - Elsevier
The education of visually impaired children remains a focal topic, and the implementation of
Braille–Chinese translation can facilitate improved understanding and learning of Braille for …
Braille–Chinese translation can facilitate improved understanding and learning of Braille for …
Hierarchical3d adapters for long video-to-text summarization
P Papalampidi, M Lapata - arXiv preprint arXiv:2210.04829, 2022 - arxiv.org
In this paper, we focus on video-to-text summarization and investigate how to best utilize
multimodal information for summarizing long inputs (eg, an hour-long TV show) into long …
multimodal information for summarizing long inputs (eg, an hour-long TV show) into long …
Reusing monolingual pre-trained models by cross-connecting seq2seq models for machine translation
J Oh, YS Choi - Applied Sciences, 2021 - mdpi.com
This work uses sequence-to-sequence (seq2seq) models pre-trained on monolingual
corpora for machine translation. We pre-train two seq2seq models with monolingual corpora …
corpora for machine translation. We pre-train two seq2seq models with monolingual corpora …
When does monolingual data help multilingual translation: The role of domain and model scale
Multilingual machine translation (MMT), trained on a mixture of parallel and monolingual
data, is key for improving translation in low-resource language pairs. However, the literature …
data, is key for improving translation in low-resource language pairs. However, the literature …
Towards Machine Translation Based on Monolingual Texts
I Kvapilíková - 2024 - dspace.cuni.cz
Title: Towards Machine Translation Based on Monolingual Texts Author: Ivana Kvapilíková
Institute: Institute of Formal and Applied Linguistics Supervisor: doc. RNDr. Ondřej Bojar, Ph …
Institute: Institute of Formal and Applied Linguistics Supervisor: doc. RNDr. Ondřej Bojar, Ph …
Learning capabilities in Transformer Neural Networks
D Variš - 2023 - dspace.cuni.cz
Title: Learning Capabilities of the Transformer Neural Networks Author: Dušan Variš
Department: Institute of Formal and Applied Linguistics Supervisor: doc. RNDr. Ondřej Bojar …
Department: Institute of Formal and Applied Linguistics Supervisor: doc. RNDr. Ondřej Bojar …