Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables
إعادة التفكير في الترجمة الآلية العصبية صفرية: من منظور المتغيرات الكامنة
460
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
الترجمة الصفرية بالرصاص، ترجمة مباشرة بين أزواج اللغة غير المرئي في التدريب، هي قدرة واعدة للترجمة الآلية العصبية متعددة اللغات (NMT). ومع ذلك، فإنه يعاني عادة من التقاط ارتباطات زائفة بين لغة الإخراج ودليل اللغة الثابتة اللغوية بسبب الهدف الأقصى لتدريب الاحتمالات، مما يؤدي إلى أداء تحويل ضعيف في الترجمة الصفرية. في هذه الورقة، نقدم هدفا مجانيا AutoNCoder بناء على لغة محورية في هدف التدريب التقليدي لتحسين دقة الترجمة على اتجاهات الطلقة الصفرية. يظهر التحليل النظري من منظور المتغيرات الكامنة أن نهجنا يزيد فعلا بشكل ضمني زيادة توزيع الاحتمالات على اتجاهات صفرية. على اثنين من مجموعات بيانات الترجمة الآلية القياسية، نوضح أن الطريقة المقترحة قادرة على القضاء بشكل فعال على الارتباط الزائفي وتتفوق بشكل كبير من الطرق التي من بين الفنادق ذات أداء رائع. يتوفر الكود الخاص بنا في https://github.com/victorwz/zs-nmt-dae.
Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the output language and language invariant semantics due to the maximum likelihood training objective, leading to poor transfer performance on zero-shot translation. In this paper, we introduce a denoising autoencoder objective based on pivot language into traditional training objective to improve the translation accuracy on zero-shot directions. The theoretical analysis from the perspective of latent variables shows that our approach actually implicitly maximizes the probability distributions for zero-shot directions. On two benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively eliminate the spurious correlations and significantly outperforms state-of-the-art methods with a remarkable performance. Our code is available at https://github.com/Victorwz/zs-nmt-dae.
References used
https://aclanthology.org/
rate research
Read More
Previous work mainly focuses on improving cross-lingual transfer for NLU tasks with a multilingual pretrained encoder (MPE), or improving the performance on supervised machine translation with BERT. However, it is under-explored that whether the MPE
can help to facilitate the cross-lingual transferability of NMT model. In this paper, we focus on a zero-shot cross-lingual transfer task in NMT. In this task, the NMT model is trained with parallel dataset of only one language pair and an off-the-shelf MPE, then it is directly tested on zero-shot language pairs. We propose SixT, a simple yet effective model for this task. SixT leverages the MPE with a two-stage training schedule and gets further improvement with a position disentangled encoder and a capacity-enhanced decoder. Using this method, SixT significantly outperforms mBART, a pretrained multilingual encoder-decoder model explicitly designed for NMT, with an average improvement of 7.1 BLEU on zero-shot any-to-English test sets across 14 source languages. Furthermore, with much less training computation cost and training data, our model achieves better performance on 15 any-to-English test sets than CRISS and m2m-100, two strong multilingual NMT baselines.
Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource-rich conditions. However, evaluations using real-world lowresource languages still result in unsatisfactory performance. This work prop
oses a novel zeroshot NMT modeling approach that learns without the now-standard assumption of a pivot language sharing parallel data with the zero-shot source and target languages. Our approach is based on three stages: initialization from any pre-trained NMT model observing at least the target language, augmentation of source sides leveraging target monolingual data, and learning to optimize the initial model to the zero-shot pair, where the latter two constitute a selflearning cycle. Empirical findings involving four diverse (in terms of a language family, script and relatedness) zero-shot pairs show the effectiveness of our approach with up to +5.93 BLEU improvement against a supervised bilingual baseline. Compared to unsupervised NMT, consistent improvements are observed even in a domain-mismatch setting, attesting to the usability of our method.
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.
Non-autoregressive neural machine translation, which decomposes the dependence on previous target tokens from the inputs of the decoder, has achieved impressive inference speedup but at the cost of inferior accuracy. Previous works employ iterative d
ecoding to improve the translation by applying multiple refinement iterations. However, a serious drawback is that these approaches expose the serious weakness in recognizing the erroneous translation pieces. In this paper, we propose an architecture named RewriteNAT to explicitly learn to rewrite the erroneous translation pieces. Specifically, RewriteNAT utilizes a locator module to locate the erroneous ones, which are then revised into the correct ones by a revisor module. Towards keeping the consistency of data distribution with iterative decoding, an iterative training strategy is employed to further improve the capacity of rewriting. Extensive experiments conducted on several widely-used benchmarks show that RewriteNAT can achieve better performance while significantly reducing decoding time, compared with previous iterative decoding strategies. In particular, RewriteNAT can obtain competitive results with autoregressive translation on WMT14 En-De, En-Fr and WMT16 Ro-En translation benchmarks.
Many NLP models operate over sequences of subword tokens produced by hand-crafted tokenization rules and heuristic subword induction algorithms. A simple universal alternative is to represent every computerized text as a sequence of bytes via UTF-8,
obviating the need for an embedding layer since there are fewer token types (256) than dimensions. Surprisingly, replacing the ubiquitous embedding layer with one-hot representations of each byte does not hurt performance; experiments on byte-to-byte machine translation from English to 10 different languages show a consistent improvement in BLEU, rivaling character-level and even standard subword-level models. A deeper investigation reveals that the combination of embeddingless models with decoder-input dropout amounts to token dropout, which benefits byte-to-byte models in particular.
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
