Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userContinual Learning in Multilingual NMT via Language-Specific Embeddings
التعلم المستمر في NMT متعدد اللغات عبر المدينات الخاصة باللغة
509
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقترح هذه الورقة تقنية لإضافة مصدر جديد أو لغة مستهدفة إلى نموذج NMT متعدد اللغات الحالي دون إعادة تدريبه في المجموعة الأولية للغات.وهي تتألف في استبدال المفردات المشتركة مع المفردات الصغيرة الخاصة باللغة ولقلها تضمين المدينات الجديدة على البيانات المتوازية باللغة الجديدة.قد يتم تدريب بعض المكونات الإضافية الخاصة باللغة على تحسين الأداء (مثل طبقات المحولات أو وحدات المحولات).لأن معلمات النموذج الأصلي لا يتم تعديلها، فإن أدائها على اللغات الأولية لا تتحلل.نظهر على مجموعتين من التجارب (نطاق صغير على محادثات تيد، واسعة النطاق على الباراسراول) أن هذا النهج ينفذ كذلك أو أفضل كمادة أكثر تكلفة؛وأنه يحتوي على أداء ممتازة للصفر: التدريب على البيانات المرن الإنجليزية يكفي للترجمة بين اللغة الجديدة وأي من اللغات الأولية.
This paper proposes a technique for adding a new source or target language to an existing multilingual NMT model without re-training it on the initial set of languages. It consists in replacing the shared vocabulary with a small language-specific vocabulary and fine-tuning the new embeddings on the new language's parallel data. Some additional language-specific components may be trained to improve performance (e.g., Transformer layers or adapter modules). Because the parameters of the original model are not modified, its performance on the initial languages does not degrade. We show on two sets of experiments (small-scale on TED Talks, and large-scale on ParaCrawl) that this approach performs as well or better as the more costly alternatives; and that it has excellent zero-shot performance: training on English-centric data is enough to translate between the new language and any of the initial languages.
References used
https://aclanthology.org/
rate research
Read More
We propose a straightforward vocabulary adaptation scheme to extend the language capacity of multilingual machine translation models, paving the way towards efficient continual learning for multilingual machine translation. Our approach is suitable f
or large-scale datasets, applies to distant languages with unseen scripts, incurs only minor degradation on the translation performance for the original language pairs and provides competitive performance even in the case where we only possess monolingual data for the new languages.
India is known as the land of many tongues and dialects. Neural machine translation (NMT) is the current state-of-the-art approach for machine translation (MT) but performs better only with large datasets which Indian languages usually lack, making t
his approach infeasible. So, in this paper, we address the problem of data scarcity by efficiently training multilingual and multilingual multi domain NMT systems involving languages of the ?????? ????????????. We are proposing the technique for using the joint domain and language tags in a multilingual setup. We draw three major conclusions from our experiments: (i) Training a multilingual system via exploiting lexical similarity based on language family helps in achieving an overall average improvement of ?.?? ???? ?????? over bilingual baselines, (ii) Technique of incorporating domain information into the language tokens helps multilingual multi-domain system in getting a significant average improvement of ? ???? ?????? over the baselines, (iii) Multistage fine-tuning further helps in getting an improvement of ?-?.? ???? ?????? for the language pair of interest.
Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and weakens its cro
ss-lingual ability, which leads to sub-optimal performance. To alleviate this problem, we leverage continual learning to preserve the original cross-lingual ability of the pre-trained model when we fine-tune it to downstream tasks. The experimental result shows that our fine-tuning methods can better preserve the cross-lingual ability of the pre-trained model in a sentence retrieval task. Our methods also achieve better performance than other fine-tuning baselines on the zero-shot cross-lingual part-of-speech tagging and named entity recognition tasks.
We present machine learning classifiers to automatically identify COVID-19 misinformation on social media in three languages: English, Bulgarian, and Arabic. We compared 4 multitask learning models for this task and found that a model trained with En
glish BERT achieves the best results for English, and multilingual BERT achieves the best results for Bulgarian and Arabic. We experimented with zero shot, few shot, and target-only conditions to evaluate the impact of target-language training data on classifier performance, and to understand the capabilities of different models to generalize across languages in detecting misinformation online. This work was performed as a submission to the shared task, NLP4IF 2021: Fighting the COVID-19 Infodemic. Our best models achieved the second best evaluation test results for Bulgarian and Arabic among all the participating teams and obtained competitive scores for English.
Adapter layers are lightweight, learnable units inserted between transformer layers. Recent work explores using such layers for neural machine translation (NMT), to adapt pre-trained models to new domains or language pairs, training only a small set
of parameters for each new setting (language pair or domain). In this work we study the compositionality of language and domain adapters in the context of Machine Translation. We aim to study, 1) parameter-efficient adaptation to multiple domains and languages simultaneously (full-resource scenario) and 2) cross-lingual transfer in domains where parallel data is unavailable for certain language pairs (partial-resource scenario). We find that in the partial resource scenario a naive combination of domain-specific and language-specific adapters often results in catastrophic forgetting' of the missing languages. We study other ways to combine the adapters to alleviate this issue and maximize cross-lingual transfer. With our best adapter combinations, we obtain improvements of 3-4 BLEU on average for source languages that do not have in-domain data. For target languages without in-domain data, we achieve a similar improvement by combining adapters with back-translation. Supplementary material is available at https://tinyurl.com/r66stbxj.
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
