Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits
لا تتبع قطاع الطرق القواعد: موازنة ترجمة آلة متعددة الأوجين مع قطاع الطرق المسلحة
288
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
غالبا ما يتم الحصول على بيانات التدريب للترجمة الآلية (MT) من العديد من الشركات الكبيرة التي هي متعددة الأوجه في الطبيعة، على سبيل المثالتحتوي على محتويات من مجالات متعددة أو مستويات مختلفة من الجودة أو التعقيد.بطبيعة الحال، لا تحدث هذه الجوانب بتردد متساو ولا هي نفسها نفسها بنفس القدر لسيناريو الاختبار في متناول اليد.في هذا العمل، نقترح تحسين هذا التوازن بشكل مشترك مع معلمات نموذج MT لتخفيف مطوري النظام من تصميم الجدول اليدوي.يتم تدريب عصري متعدد المسلح على الاختيار ديناميكيا بين الجوانب بطريقة مفيدة لنظام MT.نقيمها على ثلاثة تطبيقات مختلفة متعددة الأوجه: موازنة البيانات النسبية والبيانات التدريبية الطبيعية، أو البيانات من مجالات متعددة أو أزواج متعددة اللغات.نجد أن تعلم الفرعيد يؤدي إلى أنظمة MT تنافسية عبر المهام، ويقدم تحليلنا رؤى في استراتيجياته المستفادة ومجموعات البيانات الأساسية.
Training data for machine translation (MT) is often sourced from a multitude of large corpora that are multi-faceted in nature, e.g. containing contents from multiple domains or different levels of quality or complexity. Naturally, these facets do not occur with equal frequency, nor are they equally important for the test scenario at hand. In this work, we propose to optimize this balance jointly with MT model parameters to relieve system developers from manual schedule design. A multi-armed bandit is trained to dynamically choose between facets in a way that is most beneficial for the MT system. We evaluate it on three different multi-facet applications: balancing translationese and natural training data, or data from multiple domains or multiple language pairs. We find that bandit learning leads to competitive MT systems across tasks, and our analysis provides insights into its learned strategies and the underlying data sets.
References used
https://aclanthology.org/
rate research
Read More
Learning multilingual and multi-domain translation model is challenging as the heterogeneous and imbalanced data make the model converge inconsistently over different corpora in real world. One common practice is to adjust the share of each corpus in
the training, so that the learning process is balanced and low-resource cases can benefit from the high resource ones. However, automatic balancing methods usually depend on the intra- and inter-dataset characteristics, which is usually agnostic or requires human priors. In this work, we propose an approach, MultiUAT, that dynamically adjusts the training data usage based on the model's uncertainty on a small set of trusted clean data for multi-corpus machine translation. We experiments with two classes of uncertainty measures on multilingual (16 languages with 4 settings) and multi-domain settings (4 for in-domain and 2 for out-of-domain on English-German translation) and demonstrate our approach MultiUAT substantially outperforms its baselines, including both static and dynamic strategies. We analyze the cross-domain transfer and show the deficiency of static and similarity based methods.
When building machine translation systems, one often needs to make the best out of heterogeneous sets of parallel data in training, and to robustly handle inputs from unexpected domains in testing. This multi-domain scenario has attracted a lot of re
cent work that fall under the general umbrella of transfer learning. In this study, we revisit multi-domain machine translation, with the aim to formulate the motivations for developing such systems and the associated expectations with respect to performance. Our experiments with a large sample of multi-domain systems show that most of these expectations are hardly met and suggest that further work is needed to better analyze the current behaviour of multi-domain systems and to make them fully hold their promises.
This research deals with the importance of trade in the Levant, through the site, which produced the important commercial cities prominent, and displays the influence of Bedouin negatively and positively in the movement of trade and the danger to the movement of goods and the reputation of the state. And the impact of the road sector and the damage toll they trade, taking advantage of the geographical nature of the Levant.
Document-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information. Nevertheless, existing approaches 1) simply introduce the representations of context sentences without expli
citly characterizing the inter-sentence reasoning process; and 2) feed ground-truth target contexts as extra inputs at the training time, thus facing the problem of exposure bias. We approach these problems with an inspiration from human behavior -- human translators ordinarily emerge a translation draft in their mind and progressively revise it according to the reasoning in discourse. To this end, we propose a novel Multi-Hop Transformer (MHT) which offers NMT abilities to explicitly model the human-like draft-editing and reasoning process. Specifically, our model serves the sentence-level translation as a draft and properly refines its representations by attending to multiple antecedent sentences iteratively. Experiments on four widely used document translation tasks demonstrate that our method can significantly improve document-level translation performance and can tackle discourse phenomena, such as coreference error and the problem of polysemy.
Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between languages
hinders the model from performing uniformly across language pairs. In this paper, we propose a new learning objective for MNMT based on distributionally robust optimization, which minimizes the worst-case expected loss over the set of language pairs. We further show how to practically optimize this objective for large translation corpora using an iterated best response scheme, which is both effective and incurs negligible additional computational cost compared to standard empirical risk minimization. We perform extensive experiments on three sets of languages from two datasets and show that our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
