English
Related papers

Related papers: Patching Leaks in the Charformer for Efficient Cha…

200 papers

Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed…

Computation and Language · Computer Science 2018-05-08 Duygu Ataman , Marcello Federico

We introduce a neural machine translation model that views the input and output sentences as sequences of characters rather than words. Since word-level information provides a crucial source of bias, our input model composes representations…

Computation and Language · Computer Science 2015-11-17 Wang Ling , Isabel Trancoso , Chris Dyer , Alan W Black

Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However,…

Computation and Language · Computer Science 2021-09-14 Zewei Sun , Mingxuan Wang , Lei Li

Learning deeper models is usually a simple and effective approach to improve model performance, but deeper models have larger model parameters and are more difficult to train. To get a deeper model, simply stacking more layers of the model…

Computation and Language · Computer Science 2021-08-27 GuoLiang Li , Yiyang Li

Scaling multilingual representation learning beyond the hundred most frequent languages is challenging, in particular to cover the long tail of low-resource languages. A promising approach has been to train one-for-all multilingual models…

Computation and Language · Computer Science 2022-05-26 Kevin Heffernan , Onur Çelebi , Holger Schwenk

The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first layer and…

Computation and Language · Computer Science 2019-07-01 Denis Emelin , Ivan Titov , Rico Sennrich

Character-level Neural Machine Translation (NMT) models have recently achieved impressive results on many language pairs. They mainly do well for Indo-European language pairs, where the languages share the same writing system. However, for…

Computation and Language · Computer Science 2018-08-28 Nikola I. Nikolov , Yuhuang Hu , Mi Xue Tan , Richard H. R. Hahnloser

Neural machine translation (NMT) is one of the best methods for understanding the differences in semantic rules between two languages. Especially for Indo-European languages, subword-level models have achieved impressive results. However,…

Computation and Language · Computer Science 2019-11-11 Wei Zhang , Feifei Lin , Xiaodong Wang , Zhenshuang Liang , Zhen Huang

In this paper, we study the problem of text line recognition. Unlike most approaches targeting specific domains such as scene-text or handwritten documents, we investigate the general problem of developing a universal architecture that can…

Computer Vision and Pattern Recognition · Computer Science 2021-04-23 Daniel Hernandez Diaz , Siyang Qin , Reeve Ingle , Yasuhisa Fujii , Alessandro Bissacco

Generating longer textual sequences when conditioned on the visual information is an interesting problem to explore. The challenge here proliferate over the standard vision conditioned sentence-level generation (e.g., image or video…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Aditya Mogadala , Marius Mosbach , Dietrich Klakow

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

Machine Learning · Computer Science 2020-10-27 Minjia Zhang , Yuxiong He

Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive…

Machine Learning · Computer Science 2025-06-03 Yifan Hao , Chenlu Ye , Chi Han , Tong Zhang

Edit-based approaches have recently shown promising results on multiple monolingual sequence transduction tasks. In contrast to conventional sequence-to-sequence (Seq2Seq) models, which learn to generate text from scratch as they are…

Computation and Language · Computer Science 2022-05-11 Kostiantyn Omelianchuk , Vipul Raheja , Oleksandr Skurzhanskyi

Morphological modeling in neural machine translation (NMT) is a promising approach to achieving open-vocabulary machine translation for morphologically-rich languages. However, existing methods such as sub-word tokenization and…

Computation and Language · Computer Science 2024-04-04 Antoine Nzeyimana

The prevalent approaches of Chinese word segmentation task almost rely on the Bi-LSTM neural network. However, the methods based the Bi-LSTM have some inherent drawbacks: hard to parallel computing, little efficient in applying the Dropout…

Computation and Language · Computer Science 2019-05-22 Wei Jiang , Yan Tang

Sortformer is an encoder-based speaker diarization model designed for supervising speaker tagging in speech-to-text models. Instead of relying solely on permutation invariant loss (PIL), Sortformer introduces Sort Loss to resolve the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-22 Taejin Park , Ivan Medennikov , Kunal Dhawan , Weiqing Wang , He Huang , Nithin Rao Koluguri , Krishna C. Puvvada , Jagadeesh Balam , Boris Ginsburg

Overparameterized transformer networks have obtained state of the art results in various natural language processing tasks, such as machine translation, language modeling, and question answering. These models contain hundreds of millions of…

Machine Learning · Computer Science 2019-09-26 Angela Fan , Edouard Grave , Armand Joulin

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

Computation and Language · Computer Science 2022-03-25 Le Hou , Richard Yuanzhe Pang , Tianyi Zhou , Yuexin Wu , Xinying Song , Xiaodan Song , Denny Zhou

Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or edges as separate tokens. This approach leads to…

Machine Learning · Computer Science 2023-10-04 Zihan Pengmei , Zimu Li , Chih-chan Tien , Risi Kondor , Aaron R. Dinner

Degraded images commonly exist in the general sources of character images, leading to unsatisfactory character recognition results. Existing methods have dedicated efforts to restoring degraded character images. However, the denoising…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Daqian Shi , Xiaolei Diao , Lida Shi , Hao Tang , Yang Chi , Chuntao Li , Hao Xu
‹ Prev 1 4 5 6 7 8 10 Next ›