EvolveMT: an Ensemble MT Engine Improving Itself with Usage Only
- URL: http://arxiv.org/abs/2306.11823v1
- Date: Tue, 20 Jun 2023 18:32:30 GMT
- Title: EvolveMT: an Ensemble MT Engine Improving Itself with Usage Only
- Authors: Kamer Ali Yuksel, Ahmet Gunduz, Mohamed Al-Badrashiny, Shreyas Sharma,
Hassan Sawaf
- Abstract summary: This paper presents EvolveMT for efficiently combining multiple machine translation (MT) engines.
The proposed system selects the output from a single engine for each segment by utilizing online learning techniques to predict the most suitable system for every translation request.
- Score: 3.1498833540989413
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: This paper presents EvolveMT for efficiently combining multiple machine
translation (MT) engines. The proposed system selects the output from a single
engine for each segment by utilizing online learning techniques to predict the
most suitable system for every translation request. A neural quality estimation
metric supervises the method without requiring reference translations. The
online learning capability of this system allows for dynamic adaptation to
alterations in the domain or machine translation engines, thereby obviating the
necessity for additional training. EvolveMT selects a subset of translation
engines to be called based on the source sentence features. The degree of
exploration is configurable according to the desired quality-cost trade-off.
Results from custom datasets demonstrate that EvolveMT achieves similar
translation accuracy at a lower cost than selecting the best translation of
each segment from all translations using an MT quality estimator. To our
knowledge, EvolveMT is the first meta MT system that adapts itself after
deployment to incoming translation requests from the production environment
without needing costly retraining on human feedback.
Related papers
- Towards Zero-Shot Multimodal Machine Translation [64.9141931372384]
We propose a method to bypass the need for fully supervised data to train multimodal machine translation systems.
Our method, called ZeroMMT, consists in adapting a strong text-only machine translation (MT) model by training it on a mixture of two objectives.
To prove that our method generalizes to languages with no fully supervised training data available, we extend the CoMMuTE evaluation dataset to three new languages: Arabic, Russian and Chinese.
arXiv Detail & Related papers (2024-07-18T15:20:31Z) - Segment-Based Interactive Machine Translation for Pre-trained Models [2.0871483263418806]
We explore the use of pre-trained large language models (LLM) in interactive machine translation environments.
The system generates perfect translations interactively using the feedback provided by the user at each iteration.
We compare the performance of mBART, mT5 and a state-of-the-art (SoTA) machine translation model on a benchmark dataset regarding user effort.
arXiv Detail & Related papers (2024-07-09T16:04:21Z) - Active Learning for Neural Machine Translation [0.0]
We incorporated a technique known Active Learning with the NMT toolkit Joey NMT to reach sufficient accuracy and robust predictions of low-resource language translation.
This work uses transformer-based NMT systems; baseline model (BM), fully trained model (FTM), active learning least confidence based model (ALLCM) and active learning margin sampling based model (ALMSM) when translating English to Hindi.
arXiv Detail & Related papers (2022-12-30T17:04:01Z) - Towards Reinforcement Learning for Pivot-based Neural Machine
Translation with Non-autoregressive Transformer [49.897891031932545]
Pivot-based neural machine translation (NMT) is commonly used in low-resource setups.
We present an end-to-end pivot-based integrated model, enabling training on source-target data.
arXiv Detail & Related papers (2021-09-27T14:49:35Z) - Non-Parametric Online Learning from Human Feedback for Neural Machine
Translation [54.96594148572804]
We study the problem of online learning with human feedback in the human-in-the-loop machine translation.
Previous methods require online model updating or additional translation memory networks to achieve high-quality performance.
We propose a novel non-parametric online learning method without changing the model structure.
arXiv Detail & Related papers (2021-09-23T04:26:15Z) - Language Modeling, Lexical Translation, Reordering: The Training Process
of NMT through the Lens of Classical SMT [64.1841519527504]
neural machine translation uses a single neural network to model the entire translation process.
Despite neural machine translation being de-facto standard, it is still not clear how NMT models acquire different competences over the course of training.
arXiv Detail & Related papers (2021-09-03T09:38:50Z) - Pre-training Multilingual Neural Machine Translation by Leveraging
Alignment Information [72.2412707779571]
mRASP is an approach to pre-train a universal multilingual neural machine translation model.
We carry out experiments on 42 translation directions across a diverse setting, including low, medium, rich resource, and as well as transferring to exotic language pairs.
arXiv Detail & Related papers (2020-10-07T03:57:54Z) - Selecting Backtranslated Data from Multiple Sources for Improved Neural
Machine Translation [8.554761233491236]
We analyse the impact that data translated with rule-based, phrase-based statistical and neural MT systems has on new MT systems.
We exploit different data selection strategies in order to reduce the amount of data used, while at the same time maintaining high-quality MT systems.
arXiv Detail & Related papers (2020-05-01T10:50:53Z) - Explicit Reordering for Neural Machine Translation [50.70683739103066]
In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency.
We propose a novel reordering method to explicitly model this reordering information for the Transformer-based NMT.
The empirical results on the WMT14 English-to-German, WAT ASPEC Japanese-to-English, and WMT17 Chinese-to-English translation tasks show the effectiveness of the proposed approach.
arXiv Detail & Related papers (2020-04-08T05:28:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.