Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOn the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation
على التكامل بين ما قبل التدريب والترجمة الخلفية للترجمة الآلية العصبية
369
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
ما قبل التدريب (PT) والترجمة الخلفي (BT) هي طريقتان بسيطان وقويهما لاستخدام البيانات الأولية لتحسين الأداء النموذجي للترجمة الآلية العصبية (NMT).تأخذ هذه الورقة الخطوة الأولى للتحقيق في التكامل بين PT و BT.نقدم اثنين من المهام التحقيق الخاصة ب PT و BT على التوالي وتجد أن PT يساهم بشكل أساسي في وحدة التشفير أثناء قيام BT بتجلب المزيد من الفوائد إلى وحدة فك الترميز.تظهر النتائج التجريبية أن PT و BT مكملة بشكل جيد مع بعضها البعض، وإنشاء عروض أحدث على المعايير WMT16 الإنجليزية والرومانية والروسية.من خلال تحليلات واسعة النطاق على عصالة الجملة وتيرة الكلمة، فإننا نوضح أيضا أن الجمع بين الموسومة BT مع PT هو أكثر فائدة تكاملها، مما يؤدي إلى جودة ترجمة أفضل.شفرة المصدر متاحة بحرية في HTTPS://github.com/sunbowliu/ptvsbt.
Pre-training (PT) and back-translation (BT) are two simple and powerful methods to utilize monolingual data for improving the model performance of neural machine translation (NMT). This paper takes the first step to investigate the complementarity between PT and BT. We introduce two probing tasks for PT and BT respectively and find that PT mainly contributes to the encoder module while BT brings more benefits to the decoder. Experimental results show that PT and BT are nicely complementary to each other, establishing state-of-the-art performances on the WMT16 English-Romanian and English-Russian benchmarks. Through extensive analyses on sentence originality and word frequency, we also demonstrate that combining Tagged BT with PT is more helpful to their complementarity, leading to better translation quality. Source code is freely available at https://github.com/SunbowLiu/PTvsBT.
References used
https://aclanthology.org/
rate research
Read More
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks. However, in real-world scenarios, massive monolingual corpora do not exist for some extreme
ly low-resource languages such as Estonian, and UNMT systems usually perform poorly when there is not adequate training corpus for one language. In this paper, we first define and analyze the unbalanced training data scenario for UNMT. Based on this scenario, we propose UNMT self-training mechanisms to train a robust UNMT system and improve its performance in this case. Experimental results on several language pairs show that the proposed methods substantially outperform conventional UNMT systems.
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.
Recent research questions the importance of the dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns. In this paper, we push further in this research line and propose a novel substitute
mechanism for self-attention: Recurrent AtteNtion (RAN) . RAN directly learns attention weights without any token-to-token interaction and further improves their capacity by layer-to-layer interaction. Across an extensive set of experiments on 10 machine translation tasks, we find that RAN models are competitive and outperform their Transformer counterpart in certain scenarios, with fewer parameters and inference time. Particularly, when apply RAN to the decoder of Transformer, there brings consistent improvements by about +0.5 BLEU on 6 translation tasks and +1.0 BLEU on Turkish-English translation task. In addition, we conduct extensive analysis on the attention weights of RAN to confirm their reasonableness. Our RAN is a promising alternative to build more effective and efficient NMT models.
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.
Most current neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to-left. In this work, we propose a novel method that breaks up the limitation of these decoding orders, called Smart-Start decoding. Mor
e specifically, our method first predicts a median word. It starts to decode the words on the right side of the median word and then generates words on the left. We evaluate the proposed Smart-Start decoding method on three datasets. Experimental results show that the proposed method can significantly outperform strong baseline models.
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
