Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMulti-Hop Transformer for Document-Level Machine Translation
محول قفزة متعددة للترجمة آلة على مستوى المستند
565
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أثبتت الترجمة الآلية النموذجية على مستوى المستند (NMT) أنها ذات قيمة عميقة لفعاليتها في التقاط المعلومات السياقية. ومع ذلك، فإن الأساليب الحالية 1) تعرض ببساطة تمثيل أحكام السياق دون تمييز عملية التفكير بين الجملة؛ و 2) تغذية السياقات المستهدفة في الحقيقة كدخلات إضافية في وقت التدريب، وبالتالي تواجه مشكلة تحيز التعرض. ونحن نقترب من هذه المشاكل مع إلهام من السلوك البشري - المترجمين البشري يظهر عادة مشروع ترجمة في أذهانهم وتنقيحها تدريجيا وفقا للمنطق في الخطاب. تحقيقا لهذه الغاية، نقترح محول رواية متعددة القفز (MHT) الذي يوفر قدرات NMT على نموذج عملية التحرير والتفكير الذي يشبه الإنسان بشكل صريح. على وجه التحديد، يخدم نموذجنا الترجمة على مستوى الجملة كمسودة ويحدد خصوصياتها بشكل صحيح من خلال حضور جمل متعددة غير متجانسة تكرارا. توضح التجارب على أربعة مهام ترجمة مستندات مستعملة على نطاق واسع أن طريقتنا يمكن أن تحسن بشكل كبير من أداء الترجمة على مستوى المستندات ويمكنها معالجة ظواهر الخطاب، مثل خطأ COMARACARE ومشكلة Polysemy.
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 explicitly 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.
References used
https://aclanthology.org/
rate research
Read More
Recently a number of approaches have been proposed to improve translation performance for document-level neural machine translation (NMT). However, few are focusing on the subject of lexical translation consistency. In this paper we apply one transla
tion per discourse'' in NMT, and aim to encourage lexical translation consistency for document-level NMT. This is done by first obtaining a word link for each source word in a document, which tells the positions where the source word appears. Then we encourage the translation of those words within a link to be consistent in two ways. On the one hand, when encoding sentences within a document we properly share context information of those words. On the other hand, we propose an auxiliary loss function to better constrain that their translation should be consistent. Experimental results on Chinese↔English and English→French translation tasks show that our approach not only achieves state-of-the-art performance in BLEU scores, but also greatly improves lexical consistency in translation.
The choice of parameter sharing strategy in multilingual machine translation models determines how optimally parameter space is used and hence, directly influences ultimate translation quality. Inspired by linguistic trees that show the degree of rel
atedness between different languages, the new general approach to parameter sharing in multilingual machine translation was suggested recently. The main idea is to use these expert language hierarchies as a basis for multilingual architecture: the closer two languages are, the more parameters they share. In this work, we test this idea using the Transformer architecture and show that despite the success in previous work there are problems inherent to training such hierarchical models. We demonstrate that in case of carefully chosen training strategy the hierarchical architecture can outperform bilingual models and multilingual models with full parameter sharing.
Document machine translation aims to translate the source sentence into the target language in the presence of additional contextual information. However, it typically suffers from a lack of doc-level bilingual data. To remedy this, here we propose a
simple yet effective context-interactive pre-training approach, which targets benefiting from external large-scale corpora. The proposed model performs inter sentence generation to capture the cross-sentence dependency within the target document, and cross sentence translation to make better use of valuable contextual information. Comprehensive experiments illustrate that our approach can achieve state-of-the-art performance on three benchmark datasets, which significantly outperforms a variety of baselines.
It has been widely recognized that syntax information can help end-to-end neural machine translation (NMT) systems to achieve better translation. In order to integrate dependency information into Transformer based NMT, existing approaches either expl
oit words' local head-dependent relations, ignoring their non-local neighbors carrying important context; or approximate two words' syntactic relation by their relative distance on the dependency tree, sacrificing exactness. To address these issues, we propose global positional encoding for dependency tree, a new scheme that facilitates syntactic relation modeling between any two words with keeping exactness and without immediate neighbor constraint. Experiment results on NC11 German→English, English→German and WMT English→German datasets show that our approach is more effective than the above two strategies. In addition, our experiments quantitatively show that compared with higher layers, lower layers of the model are more proper places to incorporate syntax information in terms of each layer's preference to the syntactic pattern and the final performance.
Recent studies emphasize the need of document context in human evaluation of machine translations, but little research has been done on the impact of user interfaces on annotator productivity and the reliability of assessments. In this work, we compa
re human assessment data from the last two WMT evaluation campaigns collected via two different methods for document-level evaluation. Our analysis shows that a document-centric approach to evaluation where the annotator is presented with the entire document context on a screen leads to higher quality segment and document level assessments. It improves the correlation between segment and document scores and increases inter-annotator agreement for document scores but is considerably more time consuming for annotators.
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
