Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userIITP-MT at WAT2021: Indic-English Multilingual Neural Machine Translation using Romanized Vocabulary
IITP-MT في Wat2021: الترجمة الآلية العصبية متعددة اللغات Water-English باستخدام المفردات اللغوية
305
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف هذه الورقة أن الأنظمة المقدمة إلى المهمة المشتركة Wat 2021 Multiindicmt بواسطة فريق IITP-MT.نحن نقدم اثنين من أنظمة الترجمة الآلية العصبية متعددة اللغات (NMT) (Inster-to-English والإنجليزية إلى MEDER).ننهي جميع بيانات MED وتخلق المفردات الفرعية التي يتم مشاركتها بين جميع لغات ISS.نحن نستخدم نهج الترجمة الخلفي لتوليد البيانات الاصطناعية التي يتم إلحاقها بالتوازي Corpus وتستخدم لتدريب نماذجنا.يتم تقييم النماذج باستخدام درجات Bleu و Libes و AMFM مع نموذج MEDER-To-To-English يحقق 40.08 Bleu للزوج الهندي والإنجليزي ونموذج اللغة الإنجليزية إلى MERS لتحقيق 34.48 بلو للزوج باللغة الإنجليزية الهندية.ومع ذلك، نلاحظ أن مفردات الكلمة الفرعية المشتركة لا تساعد النموذج الإنجليزي إلى التروس في وقت الجيل، مما أدى إلى إنتاج ترجمات ذات نوعية رديئة للتاميل والتيلجو وميلايالام إلى أزواج باللغة الإنجليزية مع درجة بلو 8.51 و 6.25 و 3.79على التوالى.
This paper describes the systems submitted to WAT 2021 MultiIndicMT shared task by IITP-MT team. We submit two multilingual Neural Machine Translation (NMT) systems (Indic-to-English and English-to-Indic). We romanize all Indic data and create subword vocabulary which is shared between all Indic languages. We use back-translation approach to generate synthetic data which is appended to parallel corpus and used to train our models. The models are evaluated using BLEU, RIBES and AMFM scores with Indic-to-English model achieving 40.08 BLEU for Hindi-English pair and English-to-Indic model achieving 34.48 BLEU for English-Hindi pair. However, we observe that the shared romanized subword vocabulary is not helping English-to-Indic model at the time of generation, leading it to produce poor quality translations for Tamil, Telugu and Malayalam to English pairs with BLEU score of 8.51, 6.25 and 3.79 respectively.
References used
https://aclanthology.org/
rate research
Read More
Code-mixing has become a moving method of communication among multilingual speakers. Most of the social media content of the multilingual societies are written in code-mixed text. However, most of the current translation systems neglect to convert co
de-mixed texts to a standard language. Most of the user written code-mixed content in social media remains unprocessed due to the unavailability of linguistic resource such as parallel corpus. This paper proposes a Neural Machine Translation(NMT) model to translate the Sinhala-English code-mixed text to the Sinhala language. Due to the limited resources available for Sinhala-English code-mixed(SECM) text, a parallel corpus is created with SECM sentences and Sinhala sentences. Srilankan social media sites contain SECM texts more frequently than the standard languages. The model proposed for code-mixed text translation in this study is a combination of Encoder-Decoder framework with LSTM units and Teachers Forcing Algorithm. The translated sentences from the model are evaluated using BLEU(Bilingual Evaluation Understudy) metric. Our model achieved a remarkable BLEU score for the translation.
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.
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.
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.
Machine translation performs automatic translation from one natural language to another. Neural machine translation attains a state-of-the-art approach in machine translation, but it requires adequate training data, which is a severe problem for low-
resource language pairs translation. The concept of multimodal is introduced in neural machine translation (NMT) by merging textual features with visual features to improve low-resource pair translation. WAT2021 (Workshop on Asian Translation 2021) organizes a shared task of multimodal translation for English to Hindi. We have participated the same with team name CNLP-NITS-PP in two submissions: multimodal and text-only NMT. This work investigates phrase pairs injection via data augmentation approach and attains improvement over our previous work at WAT2020 on the same task in both text-only and multimodal NMT. We have achieved second rank on the challenge test set for English to Hindi multimodal translation where Bilingual Evaluation Understudy (BLEU) score of 39.28, Rank-based Intuitive Bilingual Evaluation Score (RIBES) 0.792097, and Adequacy-Fluency Metrics (AMFM) score 0.830230 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
