حققت الترجمة الآلية العصبية متعددة اللغات أداء ملحوظا من خلال تدريب نموذج ترجمة واحدة لغات متعددة.تصف هذه الورقة التقديم الخاص بنا (معرف الفريق: CFILT-IITB) لمكتب Multiindicmt: مهمة متعددة اللغات اللغوية في WAT 2021. نقوم بتدريب أنظمة NMT متعددة اللغات من خلال تقاسم المعلمات التشفير والكشف مع تضمين اللغة المرتبطة بكل رمزية في كل من التشفير والكشف في كل من التشفير والكشف.علاوة على ذلك، نوضح استخدام الترجمة (تحويل البرنامج النصي) لغارات الجهاز في تقليل الفجوة المعجمية لتدريب نظام NMT متعدد اللغات.علاوة على ذلك، نوضح التحسن في الأداء من خلال تدريب نظام NMT متعدد اللغات باستخدام لغات الأسرة نفسها، أي لغة ذات صلة.
Multilingual Neural Machine Translation has achieved remarkable performance by training a single translation model for multiple languages. This paper describes our submission (Team ID: CFILT-IITB) for the MultiIndicMT: An Indic Language Multilingual Task at WAT 2021. We train multilingual NMT systems by sharing encoder and decoder parameters with language embedding associated with each token in both encoder and decoder. Furthermore, we demonstrate the use of transliteration (script conversion) for Indic languages in reducing the lexical gap for training a multilingual NMT system. Further, we show improvement in performance by training a multilingual NMT system using languages of the same family, i.e., related languages.
References used
https://aclanthology.org/
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the low-resource translat
Multimodal named entity recognition (MNER) requires to bridge the gap between language understanding and visual context. While many multimodal neural techniques have been proposed to incorporate images into the MNER task, the model's ability to lever
Latent alignment objectives such as CTC and AXE significantly improve non-autoregressive machine translation models. Can they improve autoregressive models as well? We explore the possibility of training autoregressive machine translation models with
Recent impressive improvements in NLP, largely based on the success of contextual neural language models, have been mostly demonstrated on at most a couple dozen high- resource languages. Building language mod- els and, more generally, NLP systems fo
How difficult is it for English-as-a-second language (ESL) learners to read noisy English texts? Do ESL learners need lexical normalization to read noisy English texts? These questions may also affect community formation on social networking sites wh