Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userExploring the Importance of Source Text in Automatic Post-Editing for Context-Aware Machine Translation
استكشاف أهمية النص المصدر في التحرير التلقائي للترجمة الآلية للترجمة الآلية
327
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تتطلب الترجمة الدقيقة معلومات على مستوى المستندات، والتي يتم تجاهلها بواسطة الترجمة الآلية على مستوى الجملة.لقد أظهر العمل الحديث أن الاتساق على مستوى المستند يمكن تحسينه باستخدام معلومات ما بعد التحرير التلقائي باستخدام معلومات اللغة المستهدفة فقط (TL).ندرس نموذج قرد موسع يدمج سياق المصدر.يكشف التقييم البشري للطلاقة والكفاة باللغة الإنجليزية - الترجمة الروسية الإنجليزية أن النموذج الذي يتمتع بالوصول إلى سياق المصدر يتفوق بشكل كبير على قرد أحادي الأحادي من حيث الكفاية، وهو تأثير تجاهله إلى حد كبير بواسطة مقاييس التقييم التلقائي إلى حد كبير.تظهر نتائجنا أن نمذجة TL فقط يزيد الطلاقة دون تحسين كفاية، مما يدل على الحاجة إلى تكييف النص المصدر لتحرير ما بعد التحرير التلقائي.كما أنها تسليط الضوء على النقاط العمياء في الأساليب التلقائية للتقييم المستهدف وإظهار الحاجة إلى تقييم بشري لتقييم جودة الترجمة على مستوى المستند بشكل موثوق.
Accurate translation requires document-level information, which is ignored by sentence-level machine translation. Recent work has demonstrated that document-level consistency can be improved with automatic post-editing (APE) using only target-language (TL) information. We study an extended APE model that additionally integrates source context. A human evaluation of fluency and adequacy in English--Russian translation reveals that the model with access to source context significantly outperforms monolingual APE in terms of adequacy, an effect largely ignored by automatic evaluation metrics. Our results show that TL-only modelling increases fluency without improving adequacy, demonstrating the need for conditioning on source text for automatic post-editing. They also highlight blind spots in automatic methods for targeted evaluation and demonstrate the need for human assessment to evaluate document-level translation quality reliably.
References used
https://aclanthology.org/
rate research
Read More
Automatic post-editing (APE) models are usedto correct machine translation (MT) system outputs by learning from human post-editing patterns. We present the system used in our submission to the WMT'21 Automatic Post-Editing (APE) English-German (En-De
) shared task. We leverage the state-of-the-art MT system (Ng et al., 2019) for this task. For further improvements, we adapt the MT model to the task domain by using WikiMatrix (Schwenket al., 2021) followed by fine-tuning with additional APE samples from previous editions of the shared task (WMT-16,17,18) and ensembling the models. Our systems beat the baseline on TER scores on the WMT'21 test set.
Multiple parallel attention mechanisms that use multiple attention heads facilitate greater performance of the Transformer model for various applications e.g., Neural Machine Translation (NMT), text classification. In multi-head attention mechanism,
different heads attend to different parts of the input. However, the limitation is that multiple heads might attend to the same part of the input, resulting in multiple heads being redundant. Thus, the model resources are under-utilized. One approach to avoid this is to prune least important heads based on certain importance score. In this work, we focus on designing a Dynamic Head Importance Computation Mechanism (DHICM) to dynamically calculate the importance of a head with respect to the input. Our insight is to design an additional attention layer together with multi-head attention, and utilize the outputs of the multi-head attention along with the input, to compute the importance for each head. Additionally, we add an extra loss function to prevent the model from assigning same score to all heads, to identify more important heads and improvise performance. We analyzed performance of DHICM for NMT with different languages. Experiments on different datasets show that DHICM outperforms traditional Transformer-based approach by large margin, especially, when less training data is available.
The development of Translation Technologies, like Translation Memory and Machine Translation, has completely changed the translation industry and translator's workflow in the last decades. Nevertheless, TM and MT have been developed separately until
very recently. This ongoing project will study the external integration of TM and MT, examining if the productivity and post-editing efforts of translators are higher or lower than using only TM. To this end, we will conduct an experiment where Translation students and professional translators will be asked to translate two short texts; then we will check the post-editing efforts (temporal, technical and cognitive efforts) and the quality of the translated texts.
This paper introduces data on translation trainees' perceptions of the MTPE process and implications on training in this field. This study aims to analyse trainees' performance of three MTPE tasks the English-Polish language pair and post-tasks inter
views to determine the need to promote machine translation post-editing skills in educating translation students. Since very little information concerning MTPE training is available, this study may be found advantageous.
Neural machine translation (NMT) models are data-driven and require large-scale training corpus. In practical applications, NMT models are usually trained on a general domain corpus and then fine-tuned by continuing training on the in-domain corpus.
However, this bears the risk of catastrophic forgetting that the performance on the general domain is decreased drastically. In this work, we propose a new continual learning framework for NMT models. We consider a scenario where the training is comprised of multiple stages and propose a dynamic knowledge distillation technique to alleviate the problem of catastrophic forgetting systematically. We also find that the bias exists in the output linear projection when fine-tuning on the in-domain corpus, and propose a bias-correction module to eliminate the bias. We conduct experiments on three representative settings of NMT application. Experimental results show that the proposed method achieves superior performance compared to baseline models in all 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
