Neural machine translation: A review

F Stahlberg - Journal of Artificial Intelligence Research, 2020 - jair.org
The field of machine translation (MT), the automatic translation of written text from one
natural language into another, has experienced a major paradigm shift in recent years …

Text summarization method based on double attention pointer network

Z Li, Z Peng, S Tang, C Zhang, H Ma - IEEE Access, 2020 - ieeexplore.ieee.org
A good document summary should summarize the core content of the text. Research on
automatic text summarization attempts to solve this problem. The encoder-decoder model is …

As little as possible, as much as necessary: Detecting over-and undertranslations with contrastive conditioning

J Vamvas, R Sennrich - arXiv preprint arXiv:2203.01927, 2022 - arxiv.org
Omission and addition of content is a typical issue in neural machine translation. We
propose a method for detecting such phenomena with off-the-shelf translation models. Using …

Dynamic past and future for neural machine translation

Z Zheng, S Huang, Z Tu, XY Dai, J Chen - arXiv preprint arXiv:1904.09646, 2019 - arxiv.org
Previous studies have shown that neural machine translation (NMT) models can benefit from
explicitly modeling translated (Past) and untranslated (Future) to groups of translated and …

Improving paragraph-level question generation with extended answer network and uncertainty-aware beam search

H Zeng, Z Zhi, J Liu, B Wei - Information Sciences, 2021 - Elsevier
Question Generation (QG), which aims to generate a question given the relevant context, is
essential to build conversational and question–answering systems. Existing neural question …

Restoring and mining the records of the Joseon dynasty via neural language modeling and machine translation

K Kang, K Jin, S Yang, S Jang, J Choo… - arXiv preprint arXiv …, 2021 - arxiv.org
Understanding voluminous historical records provides clues on the past in various aspects,
such as social and political issues and even natural science facts. However, it is generally …

Modeling future cost for neural machine translation

C Duan, K Chen, R Wang, M Utiyama… - … on Audio, Speech …, 2021 - ieeexplore.ieee.org
Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural
networks to generate target translation word by word, and then make the generated word at …

Neural Machine Translation: A Review and Survey

F Stahlberg - arXiv preprint arXiv:1912.02047, 2019 - arxiv.org
The field of machine translation (MT), the automatic translation of written text from one
natural language into another, has experienced a major paradigm shift in recent years …

A continuum of generation tasks for investigating length bias and degenerate repetition

D Riley, D Chiang - arXiv preprint arXiv:2210.10817, 2022 - arxiv.org
Language models suffer from various degenerate behaviors. These differ between tasks:
machine translation (MT) exhibits length bias, while tasks like story generation exhibit …

Global-aware beam search for neural abstractive summarization

Y Ma, Z Lan, L Zong, K Huang - Advances in Neural …, 2021 - proceedings.neurips.cc
This study develops a calibrated beam-based algorithm with awareness of the global
attention distribution for neural abstractive summarization, aiming to improve the local …