English
Related papers

Related papers: Glancing Transformer for Non-Autoregressive Neural…

200 papers

Large language models (LLMs) that have been trained on multilingual but not parallel text exhibit a remarkable ability to translate between languages. We probe this ability in an in-depth study of the pathways language model (PaLM), which…

Computation and Language · Computer Science 2023-06-27 David Vilar , Markus Freitag , Colin Cherry , Jiaming Luo , Viresh Ratnakar , George Foster

Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length…

Computation and Language · Computer Science 2014-10-08 Kyunghyun Cho , Bart van Merrienboer , Dzmitry Bahdanau , Yoshua Bengio

In this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach. We are then able to employ attention-based NMT for many-to-many multilingual translation tasks. Our…

Computation and Language · Computer Science 2016-11-16 Thanh-Le Ha , Jan Niehues , Alexander Waibel

Recent progress in cross-lingual relation and event extraction use graph convolutional networks (GCNs) with universal dependency parses to learn language-agnostic sentence representations such that models trained on one language can be…

Computation and Language · Computer Science 2021-02-19 Wasi Uddin Ahmad , Nanyun Peng , Kai-Wei Chang

The prevalent approach to neural machine translation relies on bi-directional LSTMs to encode the source sentence. In this paper we present a faster and simpler architecture based on a succession of convolutional layers. This allows to…

Computation and Language · Computer Science 2017-07-26 Jonas Gehring , Michael Auli , David Grangier , Yann N. Dauphin

We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot amplification, distillation, and backtranslation. We first…

We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed…

Computation and Language · Computer Science 2019-04-05 Xing Niu , Weijia Xu , Marine Carpuat

General-purpose Large Language Models (LLMs) like GPT-4 have achieved remarkable advancements in machine translation (MT) by leveraging extensive web content. On the other hand, translation-specific LLMs are built by pre-training on…

Computation and Language · Computer Science 2024-10-30 Zhaopeng Feng , Ruizhe Chen , Yan Zhang , Zijie Meng , Zuozhu Liu

Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks. However, existing knowledge distillation has side effects, such as propagating…

Computation and Language · Computer Science 2023-08-07 Min Liu , Yu Bao , Chengqi Zhao , Shujian Huang

Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches. However, its performance drops considerably in the presence of morphologically rich languages (MRLs). Neural engines…

Computation and Language · Computer Science 2018-04-19 Peyman Passban , Qun Liu , Andy Way

Autoregressive models have been widely used in unsupervised text style transfer. Despite their success, these models still suffer from the content preservation problem that they usually ignore part of the source sentence and generate some…

Computation and Language · Computer Science 2021-06-07 Fei Huang , Zikai Chen , Chen Henry Wu , Qihan Guo , Xiaoyan Zhu , Minlie Huang

While machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) systems using monolingual…

Computation and Language · Computer Science 2021-12-28 Mikel Artetxe , Gorka Labaka , Eneko Agirre

Neural network-based language models are commonly used in rescoring approaches to improve the quality of modern automatic speech recognition (ASR) systems. Most of the existing methods are computationally expensive since they use…

Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of…

Machine Learning · Computer Science 2025-10-02 Anushka Tiwari , Sayantan Pal , Rohini K. Srihari , Kaiyi Ji

While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we…

Computation and Language · Computer Science 2018-09-06 Ankur Bapna , Mia Xu Chen , Orhan Firat , Yuan Cao , Yonghui Wu

Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence, so the reference sentence may be inappropriate for the training when…

Computation and Language · Computer Science 2022-12-01 Chenze Shao , Jinchao Zhang , Jie Zhou , Yang Feng

Transformer, based on the encoder-decoder framework, has achieved state-of-the-art performance on several natural language generation tasks. The encoder maps the words in the input sentence into a sequence of hidden states, which are then…

Computation and Language · Computer Science 2020-02-25 Rongxiang Weng , Haoran Wei , Shujian Huang , Heng Yu , Lidong Bing , Weihua Luo , Jiajun Chen

Machine translation (MT) is a technique that leverages computers to translate human languages automatically. Nowadays, neural machine translation (NMT) which models direct mapping between source and target languages with deep neural…

Computation and Language · Computer Science 2020-04-14 Jiajun Zhang , Chengqing Zong

Non-autoregressive translation (NAT) reduces the decoding latency but suffers from performance degradation due to the multi-modality problem. Recently, the structure of directed acyclic graph has achieved great success in NAT, which tackles…

Computation and Language · Computer Science 2023-07-18 Zhengrui Ma , Chenze Shao , Shangtong Gui , Min Zhang , Yang Feng

Autoregressive decoding of large language models (LLMs) is memory bandwidth bounded, resulting in high latency and significant wastes of the parallel processing power of modern accelerators. Existing methods for accelerating LLM decoding…

Machine Learning · Computer Science 2024-02-06 Yichao Fu , Peter Bailis , Ion Stoica , Hao Zhang