Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCounter-Interference Adapter for Multilingual Machine Translation
محول مكافحة تداخل الترجمة متعددة اللغات
662
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تطوير نموذج متعدد اللغات موحدة كان هدف متابعة طويلا للترجمة الآلية.ومع ذلك، فإن الأساليب الحالية تعاني من تدهور الأداء - نموذج واحد متعدد اللغات أدنى من المتدربين بشكل منفصل ثنائي اللغة على لغات الموارد الغنية.نحن نقوم بالتخمين أن مثل هذه الظاهرة من المقرر أن تدخل جلبت عن طريق التدريب المشترك مع لغات متعددة.لاستيعاب المشكلة، نقترح CAIT، وهو نموذج محول تكييف مع معلمة صغيرة للنفقات العامة للترجمة الآلية متعددة اللغات.نقيم CAIT على مجموعات بيانات معيار متعددة، بما في ذلك IWSLT، OPUS-100، و WMT.تشير التجارب إلى أن CAIT تتفوق باستمرار على خطوط أساسية قوية متعددة اللغات في 64 من إجمالي 66 اتجاهات لغة، 42 منها أعلى من 0.5 تحسين بلو.
Developing a unified multilingual model has been a long pursuing goal for machine translation. However, existing approaches suffer from performance degradation - a single multilingual model is inferior to separately trained bilingual ones on rich-resource languages. We conjecture that such a phenomenon is due to interference brought by joint training with multiple languages. To accommodate the issue, we propose CIAT, an adapted Transformer model with a small parameter overhead for multilingual machine translation. We evaluate CIAT on multiple benchmark datasets, including IWSLT, OPUS-100, and WMT. Experiments show that the CIAT consistently outperforms strong multilingual baselines on 64 of total 66 language directions, 42 of which have above 0.5 BLEU improvement.
References used
https://aclanthology.org/
rate research
Read More
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.
Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper and we propose two simple search base
d curricula -- orderings of the multilingual training data -- which help improve translation performance in conjunction with existing techniques such as fine-tuning. Additionally and we attempt to learn a curriculum for MNMT from scratch jointly with the training of the translation system using contextual multi-arm bandits. We show on the FLORES low-resource translation dataset that these learned curricula can provide better starting points for fine tuning and improve overall performance of the translation system.
Currently, multilingual machine translation is receiving more and more attention since it brings better performance for low resource languages (LRLs) and saves more space. However, existing multilingual machine translation models face a severe challe
nge: imbalance. As a result, the translation performance of different languages in multilingual translation models are quite different. We argue that this imbalance problem stems from the different learning competencies of different languages. Therefore, we focus on balancing the learning competencies of different languages and propose Competence-based Curriculum Learning for Multilingual Machine Translation, named CCL-M. Specifically, we firstly define two competencies to help schedule the high resource languages (HRLs) and the low resource languages: 1) Self-evaluated Competence, evaluating how well the language itself has been learned; and 2) HRLs-evaluated Competence, evaluating whether an LRL is ready to be learned according to HRLs' Self-evaluated Competence. Based on the above competencies, we utilize the proposed CCL-M algorithm to gradually add new languages into the training set in a curriculum learning manner. Furthermore, we propose a novel competence-aware dynamic balancing sampling strategy for better selecting training samples in multilingual training. Experimental results show that our approach has achieved a steady and significant performance gain compared to the previous state-of-the-art approach on the TED talks dataset.
In this paper, we present the details of the systems that we have submitted for the WAT 2021 MultiIndicMT: An Indic Language Multilingual Task. We have submitted two separate multilingual NMT models: one for English to 10 Indic languages and another
for 10 Indic languages to English. We discuss the implementation details of two separate multilingual NMT approaches, namely one-to-many and many-to-one, that makes use of a shared decoder and a shared encoder, respectively. From our experiments, we observe that the multilingual NMT systems outperforms the bilingual baseline MT systems for each of the language pairs under consideration.
Neural machine translation based on bilingual text with limited training data suffers from lexical diversity, which lowers the rare word translation accuracy and reduces the generalizability of the translation system. In this work, we utilise the mul
tiple captions from the Multi-30K dataset to increase the lexical diversity aided with the cross-lingual transfer of information among the languages in a multilingual setup. In this multilingual and multimodal setting, the inclusion of the visual features boosts the translation quality by a significant margin. Empirical study affirms that our proposed multimodal approach achieves substantial gain in terms of the automatic score and shows robustness in handling the rare word translation in the pretext of English to/from Hindi and Telugu translation tasks.
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
