Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTransformer with Syntactic Position Encoding for Machine Translation
محول مع ترميز موقف النحوية للترجمة الآلية
255
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
لقد تم الاعتراف على نطاق واسع بأن معلومات بناء الجملة يمكن أن تساعد في أنظمة الترجمة الآلية العصبية في نهاية إلى نهادة لتحقيق ترجمة أفضل. من أجل دمج معلومات التبعية في NMT المحول، النهج الحالية إما استغلال العلاقات المعتمدة في الرأس المحلية، تجاهل جيرانها غير المحليين الذين يحملون سياق مهم؛ أو تقريبي كلمتين "العلاقة الأساسية" من خلال المسافة النسبية الخاصة بها على شجرة التبعية، والتضحية بالضيق. لمعالجة هذه المشكلات، نقترح الترميز الموضعي العالمي لشجرة التبعية، وهو مخطط جديد يسهل نمذجة العلاقة النحوية بين أي كلمتين مع الحفاظ على الدقة ودون قيود جارتها الفورية. نتائج التجربة على NC11 الألمانية → الإنجليزية والإنجليزية → الألمانية و WMT الإنجليزية → تظهر مجموعات البيانات الألمانية أن نهجنا أكثر فعالية من الاستراتيجيتين المذكورتين أعلاه. بالإضافة إلى ذلك، نظرا لأن تجاربنا تظهر كميا أن مقارنة بطبقات أعلى، فإن الطبقات المنخفضة للنموذج هي أماكن أكثر أهمية لإدماج معلومات بناء الجملة من حيث تفضيل كل طبقة للنمط النحوي والأداء النهائي.
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 exploit 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.
References used
https://aclanthology.org/
rate research
Read More
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with noisy input for robust neural machine translation by introducing self-correcting predictors. Different from previous robust approaches, Secoco enables NMT
to explicitly correct noisy inputs and delete specific errors simultaneously with the translation decoding process. Secoco is able to achieve significant improvements over strong baselines on two real-world test sets and a benchmark WMT dataset with good interpretability. We will make our code and dataset publicly available soon.
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-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.
Abstract We introduce an Edit-Based TransfOrmer with Repositioning (EDITOR), which makes sequence generation flexible by seamlessly allowing users to specify preferences in output lexical choice. Building on recent models for non-autoregressive seque
nce generation (Gu et al., 2019), EDITOR generates new sequences by iteratively editing hypotheses. It relies on a novel reposition operation designed to disentangle lexical choice from word positioning decisions, while enabling efficient oracles for imitation learning and parallel edits at decoding time. Empirically, EDITOR uses soft lexical constraints more effectively than the Levenshtein Transformer (Gu et al., 2019) while speeding up decoding dramatically compared to constrained beam search (Post and Vilar, 2018). EDITOR also achieves comparable or better translation quality with faster decoding speed than the Levenshtein Transformer on standard Romanian-English, English-German, and English-Japanese machine translation tasks.
Introducing factors, that is to say, word features such as linguistic information referring to the source tokens, is known to improve the results of neural machine translation systems in certain settings, typically in recurrent architectures. This st
udy proposes enhancing the current state-of-the-art neural machine translation architecture, the Transformer, so that it allows to introduce external knowledge. In particular, our proposed modification, the Factored Transformer, uses linguistic factors that insert additional knowledge into the machine translation system. Apart from using different kinds of features, we study the effect of different architectural configurations. Specifically, we analyze the performance of combining words and features at the embedding level or at the encoder level, and we experiment with two different combination strategies. With the best-found configuration, we show improvements of 0.8 BLEU over the baseline Transformer in the IWSLT German-to-English task. Moreover, we experiment with the more challenging FLoRes English-to-Nepali benchmark, which includes both extremely low-resourced and very distant languages, and obtain an improvement of 1.2 BLEU
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
