Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userControlling Machine Translation for Multiple Attributes with Additive Interventions
تحكم الترجمة الآلية للحصول على سمات متعددة مع تدخلات مضافة
495
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
السيطرة الجميلة المحبوسة على مخرجات الترجمة الآلية (MT) على طول سمات متعددة أمر بالغ الأهمية للعديد من تطبيقات MT الحديثة ومتطلبات الحصول على ثقة المستخدمين. تتمثل النهج القياسي في ممارسة التحكم في MT بإعداد المدخلات بعلامة خاصة للإشارة إلى سمة الإخراج المرغوبة. على الرغم من بساطته، فإن علامات السمة لديها العديد من العيوب: يجب أن تكون القيم المستمرة في الفئات المنفصلة، وهي غير طبيعية لبعض التطبيقات؛ التدخل بين العلامات المتعددة مفهومة سيئة. نحن نبحث عن هذه المشاكل عن طريق إدخال تدخلات ذات قيمة ناقلات تسمح بالتحكم الدقيق في سمات متعددة في وقت واحد عبر مزيج خطي مرجح من المتجهات المقابلة. بالنسبة لبعض السمات، تسمح نهجنا حتى بضبط نموذج تدرب عليه دون توضيحية لدعم هذه التدخلات. في تجارب ذات ثلاث سمات (الطول والتدانة والروماتونية) واثنين من أزواج اللغة (الإنجليزية إلى الألمانية واليابانية) تحقق نماذجنا تحكما أفضل على مجموعة واسعة من المهام مقارنة بوضع العلامات، لا تتحلل جودة الترجمة عند عدم طلب أي سيطرة. أخيرا، نوضح كيفية تمكين التحكم في نموذج مدرب بالفعل بعد مرحلة صعبة رخيصة نسبيا.
Fine-grained control of machine translation (MT) outputs along multiple attributes is critical for many modern MT applications and is a requirement for gaining users' trust. A standard approach for exerting control in MT is to prepend the input with a special tag to signal the desired output attribute. Despite its simplicity, attribute tagging has several drawbacks: continuous values must be binned into discrete categories, which is unnatural for certain applications; interference between multiple tags is poorly understood. We address these problems by introducing vector-valued interventions which allow for fine-grained control over multiple attributes simultaneously via a weighted linear combination of the corresponding vectors. For some attributes, our approach even allows for fine-tuning a model trained without annotations to support such interventions. In experiments with three attributes (length, politeness and monotonicity) and two language pairs (English to German and Japanese) our models achieve better control over a wider range of tasks compared to tagging, and translation quality does not degrade when no control is requested. Finally, we demonstrate how to enable control in an already trained model after a relatively cheap fine-tuning stage.
References used
https://aclanthology.org/
rate research
Read More
Quality Estimation (QE) for Machine Translation has been shown to reach relatively high accuracy in predicting sentence-level scores, relying on pretrained contextual embeddings and human-produced quality scores. However, the lack of explanations alo
ng with decisions made by end-to-end neural models makes the results difficult to interpret. Furthermore, word-level annotated datasets are rare due to the prohibitive effort required to perform this task, while they could provide interpretable signals in addition to sentence-level QE outputs. In this paper, we propose a novel QE architecture which tackles both the word-level data scarcity and the interpretability limitations of recent approaches. Sentence-level and word-level components are jointly pretrained through an attention mechanism based on synthetic data and a set of MT metrics embedded in a common space. Our approach is evaluated on the Eval4NLP 2021 shared task and our submissions reach the first position in all language pairs. The extraction of metric-to-input attention weights show that different metrics focus on different parts of the source and target text, providing strong rationales in the decision-making process of the QE model.
The paper presents experiments in neural machine translation with lexical constraints into a morphologically rich language. In particular and we introduce a method and based on constrained decoding and which handles the inflected forms of lexical ent
ries and does not require any modification to the training data or model architecture. To evaluate its effectiveness and we carry out experiments in two different scenarios: general and domain-specific. We compare our method with baseline translation and i.e. translation without lexical constraints and in terms of translation speed and translation quality. To evaluate how well the method handles the constraints and we propose new evaluation metrics which take into account the presence and placement and duplication and inflectional correctness of lexical terms in the output sentence.
Neural machine translation based on bilingual text with limited training data suffers from lexical diversity, which lowers the rare word translation accuracy and reduces the generalizability of the translation system. In this work, we utilise the mul
tiple captions from the Multi-30K dataset to increase the lexical diversity aided with the cross-lingual transfer of information among the languages in a multilingual setup. In this multilingual and multimodal setting, the inclusion of the visual features boosts the translation quality by a significant margin. Empirical study affirms that our proposed multimodal approach achieves substantial gain in terms of the automatic score and shows robustness in handling the rare word translation in the pretext of English to/from Hindi and Telugu translation tasks.
Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper and we propose two simple search base
d curricula -- orderings of the multilingual training data -- which help improve translation performance in conjunction with existing techniques such as fine-tuning. Additionally and we attempt to learn a curriculum for MNMT from scratch jointly with the training of the translation system using contextual multi-arm bandits. We show on the FLORES low-resource translation dataset that these learned curricula can provide better starting points for fine tuning and improve overall performance of the translation system.
Machine translation usually relies on parallel corpora to provide parallel signals for training. The advent of unsupervised machine translation has brought machine translation away from this reliance, though performance still lags behind traditional
supervised machine translation. In unsupervised machine translation, the model seeks symmetric language similarities as a source of weak parallel signal to achieve translation. Chomsky's Universal Grammar theory postulates that grammar is an innate form of knowledge to humans and is governed by universal principles and constraints. Therefore, in this paper, we seek to leverage such shared grammar clues to provide more explicit language parallel signals to enhance the training of unsupervised machine translation models. Through experiments on multiple typical language pairs, we demonstrate the effectiveness of our proposed approaches.
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
