Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDistributionally Robust Multilingual Machine Translation
ترجمة آلة متعددة اللغات قوية
298
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعلم الترجمة الآلية العصبية متعددة اللغات (MNMT) ترجمة أزواج متعددة اللغات بنموذج واحد، يحتمل أن يحسن كل من الدقة وكفاءة الذاكرة للنماذج المنتشرة. ومع ذلك، فإن عدم اختلال البيانات الثقيلة بين اللغات يعوق النموذج من الأداء بشكل موحد عبر أزواج اللغة. في هذه الورقة، نقترح هدفا تعليميا جديدا ل MNMT بناء على التحسين القوي التويضي، مما يقلل من الخسارة المتوقعة الأسوأ في مجموعة أزواج اللغة. نوضح كذلك كيفية تحسين هذا الهدف من الناحية العملية للترجمة الكبيرة باستخدام مخطط أفضل استجابة مزخرف، وهو فعاليتان فعالة وتتحمل تكلفة حسابية إضافية ضئيلة مقارنة بقليل المخاطر التجريبية القياسية. نقوم بإجراء تجارب مكثفة على ثلاث مجموعات من اللغات من مجموعة بيانات وتظهر أن طريقتنا تتفوق باستمرار على أساليب خطية قوية من حيث المتوسط والأداء لكل لغة تحت كلا من إعدادات الترجمة متعددة إلى واحدة وواحدة متعددة.
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.
References used
https://aclanthology.org/
rate research
Read More
Traditional translation systems trained on written documents perform well for text-based translation but not as well for speech-based applications. We aim to adapt translation models to speech by introducing actual lexical errors from ASR and segment
ation errors from automatic punctuation into our translation training data. We introduce an inverted projection approach that projects automatically detected system segments onto human transcripts and then re-segments the gold translations to align with the projected human transcripts. We demonstrate that this overcomes the train-test mismatch present in other training approaches. The new projection approach achieves gains of over 1 BLEU point over a baseline that is exposed to the human transcripts and segmentations, and these gains hold for both IWSLT data and YouTube data.
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.
Multilingual neural machine translation models typically handle one source language at a time. However, prior work has shown that translating from multiple source languages improves translation quality. Different from existing approaches on multi-sou
rce translation that are limited to the test scenario where parallel source sentences from multiple languages are available at inference time, we propose to improve multilingual translation in a more common scenario by exploiting synthetic source sentences from auxiliary languages. We train our model on synthetic multi-source corpora and apply random masking to enable flexible inference with single-source or bi-source inputs. Extensive experiments on Chinese/English-Japanese and a large-scale multilingual translation benchmark show that our model outperforms the multilingual baseline significantly by up to +4.0 BLEU with the largest improvements on low-resource or distant language pairs.
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.
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the low-resource translat
ion by leveraging data from multiple languages. However, the performance of an MNMT model is highly dependent on the type of languages used in training, as transferring knowledge from a diverse set of languages degrades the translation performance due to negative transfer. In this paper, we propose a Hierarchical Knowledge Distillation (HKD) approach for MNMT which capitalises on language groups generated according to typological features and phylogeny of languages to overcome the issue of negative transfer. HKD generates a set of multilingual teacher-assistant models via a selective knowledge distillation mechanism based on the language groups, and then distills the ultimate multilingual model from those assistants in an adaptive way. Experimental results derived from the TED dataset with 53 languages demonstrate the effectiveness of our approach in avoiding the negative transfer effect in MNMT, leading to an improved translation performance (about 1 BLEU score in average) compared to strong baselines.
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
