Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTMU NMT System with Japanese BART for the Patent task of WAT 2021
نظام TMU NMT مع بارت اليابانية لمهمة براءات الاختراع في WAT 2021
333
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذه الورقة، نقدم نظام TMU العصبي الخاص بنا (NMT) مقدم له مهمة براءات الاختراع (اليابانية والإنجليزية الكورية اليابانية) من ورشة العمل الثامنة حول الترجمة الآسيوية (Nakazawa et al.، 2021).في الآونة الأخيرة، اقترحت عدة دراسات طرز فك التشفير المدربة مسبقا باستخدام بيانات أحادية الأونلينغ.تم عرض واحدة من النماذج المدربة مسبقا، بارت (لويس وآخرون، 2020)، لتحسين دقة الترجمة عن طريق ضبط الدقيقة مع بيانات ثنائية اللغة.ومع ذلك، قاموا بتجريد الترجمة الإنجليزية الرومانية فقط باستخدام اللغة الإنجليزية بارت.في هذه الورقة، ندرس فعالية بارت اليابانية باستخدام مكتب براءات الاختراع الياباني Corpus 2.0.تشير تجاربنا إلى أن البارت الياباني يمكنه أيضا تحسين دقة الترجمة في كل من الترجمات اليابانية اليابانية والإنجليزية الكورية.
In this paper, we introduce our TMU Neural Machine Translation (NMT) system submitted for the Patent task (Korean Japanese and English Japanese) of 8th Workshop on Asian Translation (Nakazawa et al., 2021). Recently, several studies proposed pre-trained encoder-decoder models using monolingual data. One of the pre-trained models, BART (Lewis et al., 2020), was shown to improve translation accuracy via fine-tuning with bilingual data. However, they experimented only Romanian!English translation using English BART. In this paper, we examine the effectiveness of Japanese BART using Japan Patent Office Corpus 2.0. Our experiments indicate that Japanese BART can also improve translation accuracy in both Korean Japanese and English Japanese translations.
References used
https://aclanthology.org/
rate research
Read More
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.
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 lang
uages. 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.
This paper describes the work and the systems submitted by the IIIT-Hyderbad team in the WAT 2021 MultiIndicMT shared task. The task covers 10 major languages of the Indian subcontinent. For the scope of this task, we have built multilingual systems
for 20 translation directions namely English-Indic (one-to- many) and Indic-English (many-to-one). Individually, Indian languages are resource poor which hampers translation quality but by leveraging multilingualism and abundant monolingual corpora, the translation quality can be substantially boosted. But the multilingual systems are highly complex in terms of time as well as computational resources. Therefore, we are training our systems by efficiently se- lecting data that will actually contribute to most of the learning process. Furthermore, we are also exploiting the language related- ness found in between Indian languages. All the comparisons were made using BLEU score and we found that our final multilingual sys- tem significantly outperforms the baselines by an average of 11.3 and 19.6 BLEU points for English-Indic (en-xx) and Indic-English (xx- en) directions, respectively.
This paper describes NAIST's system for the English-to-Japanese Simultaneous Text-to-text Translation Task in IWSLT 2021 Evaluation Campaign. Our primary submission is based on wait-k neural machine translation with sequence-level knowledge distillation to encourage literal translation.
Simultaneous span detection and classification is a task not currently addressed in standard NLP frameworks. The present paper describes why and how an EncoderDecoder model was used to combine span detection and classification to address subtask 2 of SemEval-2021 Task 6.
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
