Scene text detection and recognition: The deep learning era

S Long, X He, C Yao - International Journal of Computer Vision, 2021‏ - Springer
With the rise and development of deep learning, computer vision has been tremendously
transformed and reshaped. As an important research area in computer vision, scene text …

[HTML][HTML] Progress in neural NLP: modeling, learning, and reasoning

M Zhou, N Duan, S Liu, HY Shum - Engineering, 2020‏ - Elsevier
Natural language processing (NLP) is a subfield of artificial intelligence that focuses on
enabling computers to understand and process human languages. In the last five years, we …

SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

L Barrault, YA Chung, MC Meglioli, D Dale… - arxiv preprint arxiv …, 2023‏ - arxiv.org
What does it take to create the Babel Fish, a tool that can help individuals translate speech
between any two languages? While recent breakthroughs in text-based models have …

Hyporadise: An open baseline for generative speech recognition with large language models

C Chen, Y Hu, CHH Yang… - Advances in …, 2023‏ - proceedings.neurips.cc
Advancements in deep neural networks have allowed automatic speech recognition (ASR)
systems to attain human parity on several publicly available clean speech datasets …

Levenshtein transformer

J Gu, C Wang, J Zhao - Advances in neural information …, 2019‏ - proceedings.neurips.cc
Modern neural sequence generation models are built to either generate tokens step-by-step
from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this …

Achieving human parity on automatic chinese to english news translation

H Hassan, A Aue, C Chen, V Chowdhary… - arxiv preprint arxiv …, 2018‏ - arxiv.org
Machine translation has made rapid advances in recent years. Millions of people are using it
today in online translation systems and mobile applications in order to communicate across …

Deterministic non-autoregressive neural sequence modeling by iterative refinement

J Lee, E Mansimov, K Cho - arxiv preprint arxiv:1802.06901, 2018‏ - arxiv.org
We propose a conditional non-autoregressive neural sequence model based on iterative
refinement. The proposed model is designed based on the principles of latent variable …

When a good translation is wrong in context: Context-aware machine translation improves on deixis, ellipsis, and lexical cohesion

E Voita, R Sennrich, I Titov - arxiv preprint arxiv:1905.05979, 2019‏ - arxiv.org
Though machine translation errors caused by the lack of context beyond one sentence have
long been acknowledged, the development of context-aware NMT systems is hampered by …

Neural abstractive text summarization with sequence-to-sequence models

T Shi, Y Keneshloo, N Ramakrishnan… - ACM Transactions on …, 2021‏ - dl.acm.org
In the past few years, neural abstractive text summarization with sequence-to-sequence
(seq2seq) models have gained a lot of popularity. Many interesting techniques have been …

Deep reinforcement learning for sequence-to-sequence models

Y Keneshloo, T Shi, N Ramakrishnan… - IEEE transactions on …, 2019‏ - ieeexplore.ieee.org
In recent times, sequence-to-sequence (seq2seq) models have gained a lot of popularity
and provide state-of-the-art performance in a wide variety of tasks, such as machine …