paper-with-me

Papers

Generative Neural Machine Translation

2018-06-13 · NeurIPS 2018 12 · Harshil Shah, David Barber

We introduce Generative Neural Machine Translation (GNMT), a latent variable architecture which is designed to model the semantics of the source and target sentences. We modify an encoder-decoder translation model by adding a latent variable as a language agnostic representation which is encouraged to learn the meaning of the sentence. GNMT achieves competitive BLEU scores on pure translation tasks, and is superior when there are missing words in the source sentence. We augment the model to facilitate multilingual translation and semi-supervised learning without adding parameters. This framework significantly reduces overfitting when there is limited paired data available, and is effective for translating between pairs of languages not seen during training.

📄 PDF Abstract BibTeX arXiv:1806.05138

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationSentenceTranslation

Similar Papers 제목 키워드 기반

A Generative Framework for Simultaneous Machine Translation

2021-11-01 · EMNLP 2021 11 · Yishu Miao, Phil Blunsom, Lucia Specia

We propose a generative framework for simultaneous machine translation. Conventional approaches use a fixed number of source words to translate or learn dynamic policies for the number of source words by reinforcement le…

Machine Translationreinforcement-learningReinforcement Learning (RL)Translation

Quick Back-Translation for Unsupervised Machine Translation

2023-12-01 · Benjamin Brimacombe, Jiawei Zhou

The field of unsupervised machine translation has seen significant advancement from the marriage of the Transformer and the back-translation algorithm. The Transformer is a powerful generative model, and back-translation…

DecoderMachine TranslationTranslationUnsupervised Machine Translation

Improvement in Machine Translation with Generative Adversarial Networks

2021-11-30 · Jay Ahn, Hari Madhu, Viet Nguyen

In this paper, we explore machine translation improvement via Generative Adversarial Network (GAN) architecture. We take inspiration from RelGAN, a model for text generation, and NMT-GAN, an adversarial machine translati…

Generative Adversarial NetworkMachine TranslationNMTSentence+2

Neural Machine Translation with Gumbel-Greedy Decoding

2017-06-22 · Jiatao Gu, Daniel Jiwoong Im, Victor O. K. Li

Previous neural machine translation models used some heuristic search algorithms (e.g., beam search) in order to avoid solving the maximum a posteriori problem over translation sentences at test time. In this paper, we p…

Heuristic SearchMachine TranslationTranslation

A Stochastic Decoder for Neural Machine Translation

2018-05-28 · ACL 2018 7 · Philip Schulz, Wilker Aziz, Trevor Cohn

The process of translation is ambiguous, in that there are typically many valid trans- lations for a given sentence. This gives rise to significant variation in parallel cor- pora, however, most current models of machine…

DecoderMachine TranslationSentenceTranslation+2