Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userANVITA Machine Translation System for WAT 2021 MultiIndicMT Shared Task
نظام الترجمة آلة Anvita ل Wat 2021 Multiindicmt مهمة مشتركة
280
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
توضح هذه الورقة نظام Anvita-1.0 MT، Architeted for Survision To Wath2021 Multiindicmt Task من فريق Mcairt، حيث شارك الفريق في 20 اتجاهات ترجمة: الإنجليزية → Werc و Indic → الإنجليزية؛ تشدد مجموعة تشل من 10 لغات هندية. نظام Anvita-1.0 MT يتكون من نماذج NMT متعددة اللغات واحد للغة الإنجليزية → اتجاهات MEDISTION وغيرها من الإرشادات وغيرها من الإرشادات الإنجليزية مع فك التشفير المشترك، والتموين 10 أزواج اللغة والعشرون اتجاهي الترجمة. بنيت النماذج الأساسية بناء على بنية المحولات وتدريبها على Multiindicmt Wat 2021 Corpora وزيادة الترجمة والترجمة الترجمة والترجمة الخاصة بتزوير البيانات الانتقائية، وفرقة نموذجية لتحسين التعميم. بالإضافة إلى ذلك، تم تقطير Multiindicmt Wat 2021 Corpora باستخدام سلسلة من عمليات التصفية قبل طرح التدريب. anvita-1.0 حقق أعلى درجة AM-FM النتيجة للغة الإنجليزية → البنغالية، 2nd للغة الإنجليزية → التاميل و 3 للإنجليزية → الهندية، البنغالية → الإنجليزية الاتجاهات في مجموعة الاختبار الرسمية. بشكل عام، فإن الأداء الذي حققه Anvita للتشج ← اتجاهات إنجليزية أفضل نسبيا من أن الإنجليزي → اتجاهات MEDIAL لجميع أزواج اللغة 10 عند تقييمها باستخدام Bleu and Ribes، على الرغم من أن الاتجاه نفسه غير مريح باستمرار عند تقييم AM-FM نفذت. بالمقارنة مع Bleu، فإن RIBES و AM-FM تستند إلى أنفيتا أفضل نسبيا بين جميع المشاركين المهام.
This paper describes ANVITA-1.0 MT system, architected for submission to WAT2021 MultiIndicMT shared task by mcairt team, where the team participated in 20 translation directions: English→Indic and Indic→English; Indic set comprised of 10 Indian languages. ANVITA-1.0 MT system comprised of two multi-lingual NMT models one for the English→Indic directions and other for the Indic→English directions with shared encoder-decoder, catering 10 language pairs and twenty translation directions. The base models were built based on Transformer architecture and trained over MultiIndicMT WAT 2021 corpora and further employed back translation and transliteration for selective data augmentation, and model ensemble for better generalization. Additionally, MultiIndicMT WAT 2021 corpora was distilled using a series of filtering operations before putting up for training. ANVITA-1.0 achieved highest AM-FM score for English→Bengali, 2nd for English→Tamil and 3rd for English→Hindi, Bengali→English directions on official test set. In general, performance achieved by ANVITA for the Indic→English directions are relatively better than that of English→Indic directions for all the 10 language pairs when evaluated using BLEU and RIBES, although the same trend is not observed consistently when AM-FM based evaluation was carried out. As compared to BLEU, RIBES and AM-FM based scoring placed ANVITA relatively better among all the task participants.
References used
https://aclanthology.org/
rate research
Read More
This paper presents the Bering Lab's submission to the shared tasks of the 8th Workshop on Asian Translation (WAT 2021) on JPC2 and NICT-SAP. We participated in all tasks on JPC2 and IT domain tasks on NICT-SAP. Our approach for all tasks mainly focu
sed on building NMT systems in domain-specific corpora. We crawled patent document pairs for English-Japanese, Chinese-Japanese, and Korean-Japanese. After cleaning noisy data, we built parallel corpus by aligning those sentences with the sentence-level similarity scores. Also, for SAP test data, we collected the OPUS dataset including three IT domain corpora. We then trained transformer on the collected dataset. Our submission ranked 1st in eight out of fourteen tasks, achieving up to an improvement of 2.87 for JPC2 and 8.79 for NICT-SAP in BLEU score .
In this paper, we describe our submissions for the Similar Language Translation Shared Task 2021. We built 3 systems in each direction for the Tamil ⇐⇒ Telugu language pair. This paper outlines experiments with various tokenization schemes to train statistical models. We also report the configuration of the submitted systems and results produced by them.
Neural Machine Translation (NMT) is a predominant machine translation technology nowadays because of its end-to-end trainable flexibility. However, NMT still struggles to translate properly in low-resource settings specifically on distant language pa
irs. One way to overcome this is to use the information from other modalities if available. The idea is that despite differences in languages, both the source and target language speakers see the same thing and the visual representation of both the source and target is the same, which can positively assist the system. Multimodal information can help the NMT system to improve the translation by removing ambiguity on some phrases or words. We participate in the 8th Workshop on Asian Translation (WAT - 2021) for English-Hindi multimodal translation task and achieve 42.47 and 37.50 BLEU points for Evaluation and Challenge subset, respectively.
In this paper, we describe our submissions for LoResMT Shared Task @MT Summit 2021 Conference. We built statistical translation systems in each direction for English ⇐⇒ Marathi language pair. This paper outlines initial baseline experiments with vari
ous tokenization schemes to train models. Using optimal tokenization scheme we create synthetic data and further train augmented dataset to create more statistical models. Also, we reorder English to match Marathi syntax to further train another set of baseline and data augmented models using various tokenization schemes. We report configuration of the submitted systems and results produced by them.
In this paper we describe our submissions to WAT-2021 (Nakazawa et al., 2021) for English-to-Myanmar language (Burmese) task. Our team, ID: YCC-MT1'', focused on bringing transliteration knowledge to the decoder without changing the model. We manuall
y extracted the transliteration word/phrase pairs from the ALT corpus and applying XML markup feature of Moses decoder (i.e. -xml-input exclusive, -xml-input inclusive). We demonstrate that hybrid translation technique can significantly improve (around 6 BLEU scores) the baseline of three well-known Phrase-based SMT'', Operation Sequence Model'' and Hierarchical Phrase-based SMT''. Moreover, this simple hybrid method achieved the second highest results among the submitted MT systems for English-to-Myanmar WAT2021 translation share task according to BLEU (Papineni et al., 2002) and AMFM scores (Banchs et al., 2015).
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
