Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTranslation-based Supervision for Policy Generation in Simultaneous Neural Machine Translation
الإشراف القائم على الترجمة عن جيل السياسة في الترجمة الآلية العصبية في وقت واحد
425
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في الترجمة الآلية المتزامنة، والعثور على وكيل مع تسلسل العمل الأمثل للقراءة والكتابة التي تحتفظ بمستوى عال من جودة الترجمة مع التقليل من التأخر المتوسط في إنتاج الرموز المستهدفة لا يزال مشكلة صعبة للغاية. نقترح نهج تعليمي تحت إشراف رواية لتدريب وكيل يمكنه اكتشاف الحد الأدنى لعدد القراءة المطلوبة لتوليد كل رمزية مستهدفة من خلال مقارنة الترجمات المتزامنة ضد ترجمات الجملة الكاملة أثناء التدريب لإنشاء تسلسل عمل أوراكل. يمكن بعد ذلك استخدام تسلسل أوراكل هذه لتدريب نموذج إشراف لتوليد العمل في وقت الاستدلال. يوفر نهجنا بديلا عن طرق التشكيل الحالية في الترجمة المتزامنة من خلال تقديم هدف تدريب جديد، وهو أمر أسهل للتدريب من المحاولات السابقة في تدريب الوكيل باستخدام تقنيات تعليم التعزيز لهذه المهمة. تظهر نتائجنا التجريبية أن طريقة التدريب الجديدة لتوليد العمل تنتج ترجمات عالية الجودة مع تقليل التأخر المتوسط في الترجمة الفورية.
In simultaneous machine translation, finding an agent with the optimal action sequence of reads and writes that maintain a high level of translation quality while minimizing the average lag in producing target tokens remains an extremely challenging problem. We propose a novel supervised learning approach for training an agent that can detect the minimum number of reads required for generating each target token by comparing simultaneous translations against full-sentence translations during training to generate oracle action sequences. These oracle sequences can then be used to train a supervised model for action generation at inference time. Our approach provides an alternative to current heuristic methods in simultaneous translation by introducing a new training objective, which is easier to train than previous attempts at training the agent using reinforcement learning techniques for this task. Our experimental results show that our novel training method for action generation produces much higher quality translations while minimizing the average lag in simultaneous translation.
References used
https://aclanthology.org/
rate research
Read More
In a real-time simultaneous translation setting and neural machine translation (NMT) models start generating target language tokens from incomplete source language sentences and making them harder to translate and leading to poor translation quality.
Previous research has shown that document-level NMT and comprising of sentence and context encoders and a decoder and leverages context from neighboring sentences and helps improve translation quality. In simultaneous translation settings and the context from previous sentences should be even more critical. To this end and in this paper and we propose wait-k simultaneous document-level NMT where we keep the context encoder as it is and replace the source sentence encoder and target language decoder with their wait-k equivalents. We experiment with low and high resource settings using the ALT and OpenSubtitles2018 corpora and where we observe minor improvements in translation quality. We then perform an analysis of the translations obtained using our models by focusing on sentences that should benefit from the context where we found out that the model does and in fact and benefit from context but is unable to effectively leverage it and especially in a low-resource setting. This shows that there is a need for further innovation in the way useful context is identified and leveraged.
Simultaneous translation is a task in which translation begins before the speaker has finished speaking, so it is important to decide when to start the translation process. However, deciding whether to read more input words or start to translate is d
ifficult for language pairs with different word orders such as English and Japanese. Motivated by the concept of pre-reordering, we propose a couple of simple decision rules using the label of the next constituent predicted by incremental constituent label prediction. In experiments on English-to-Japanese simultaneous translation, the proposed method outperformed baselines in the quality-latency trade-off.
For most language combinations and parallel data is either scarce or simply unavailable. To address this and unsupervised machine translation (UMT) exploits large amounts of monolingual data by using synthetic data generation techniques such as back-
translation and noising and while self-supervised NMT (SSNMT) identifies parallel sentences in smaller comparable data and trains on them. To this date and the inclusion of UMT data generation techniques in SSNMT has not been investigated. We show that including UMT techniques into SSNMT significantly outperforms SSNMT (up to +4.3 BLEU and af2en) as well as statistical (+50.8 BLEU) and hybrid UMT (+51.5 BLEU) baselines on related and distantly-related and unrelated language pairs.
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.
The neural machine translation approach has gained popularity in machine translation because of its context analysing ability and its handling of long-term dependency issues. We have participated in the WMT21 shared task of similar language translati
on on a Tamil-Telugu pair with the team name: CNLP-NITS. In this task, we utilized monolingual data via pre-train word embeddings in transformer model based neural machine translation to tackle the limitation of parallel corpus. Our model has achieved a bilingual evaluation understudy (BLEU) score of 4.05, rank-based intuitive bilingual evaluation score (RIBES) score of 24.80 and translation edit rate (TER) score of 97.24 for both Tamil-to-Telugu and Telugu-to-Tamil translations respectively.
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
