Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRakuten's Participation in WAT 2021: Examining the Effectiveness of Pre-trained Models for Multilingual and Multimodal Machine Translation
مشاركة Rakuten في Wat 2021: فحص فعالية النماذج المدربة مسبقا للترجمة متعددة اللغات والمعددية
443
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقدم هذه الورقة مشاركة أنظمة الترجمة الآلية العصبية في مهام الترجمة المشتركة WAT 2021 (معرف الفريق: ساكورا).شاركنا في (I) NIST-SAP، (2) ترجمة متعددة الوسائط اليابانية-الإنجليزية، (III) متعددة اللغات، و (4) مهام الترجمة الإنجليزية Myanmar-English.مناهج متعددة اللغات مثل MBART (ليو وآخرون.، 2020) قادرون على تدريب ما قبل التدريب على نموذج تسلسل كامل وتسلسل إلى متعدد اللغات من خلال الأهداف المنقحية، مما يجعلها نقطة انطلاق رائعة لبناء أنظمة الترجمة متعددة اللغات.التركيز الرئيسي لدينا في هذا العمل هو التحقيق في فعالية Finetuning متعددة اللغات في نموذج لغة متعددة اللغات على مهام الترجمة المختلفة، بما في ذلك ترجمة الموارد المنخفضة والمتعددة الوسائط والمختلطة.نسمح أيضا نهجا متعدد الوسائط بناء على التمثيل المرئي العالمي (تشانغ وآخرون، 2019) ومقارنة أدائه ضد نهج غير مهني بناء على MBART بمفرده.
This paper introduces our neural machine translation systems' participation in the WAT 2021 shared translation tasks (team ID: sakura). We participated in the (i) NICT-SAP, (ii) Japanese-English multimodal translation, (iii) Multilingual Indic, and (iv) Myanmar-English translation tasks. Multilingual approaches such as mBART (Liu et al., 2020) are capable of pre-training a complete, multilingual sequence-to-sequence model through denoising objectives, making it a great starting point for building multilingual translation systems. Our main focus in this work is to investigate the effectiveness of multilingual finetuning on such a multilingual language model on various translation tasks, including low-resource, multimodal, and mixed-domain translation. We further explore a multimodal approach based on universal visual representation (Zhang et al., 2019) and compare its performance against a unimodal approach based on mBART alone.
References used
https://aclanthology.org/
rate research
Read More
Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However, directly c
onnecting BERT as an encoder and GPT as a decoder can be challenging in machine translation, for GPT-like models lack a cross-attention component that is needed in seq2seq decoders. In this paper, we propose Graformer to graft separately pre-trained (masked) language models for machine translation. With monolingual data for pre-training and parallel data for grafting training, we maximally take advantage of the usage of both types of data. Experiments on 60 directions show that our method achieves average improvements of 5.8 BLEU in x2en and 2.9 BLEU in en2x directions comparing with the multilingual Transformer of the same size.
In this paper, we report the experimental results of Machine Translation models conducted by a NECTEC team for the translation tasks of WAT-2021. Basically, our models are based on neural methods for both directions of English-Myanmar and Myanmar-Eng
lish language pairs. Most of the existing Neural Machine Translation (NMT) models mainly focus on the conversion of sequential data and do not directly use syntactic information. However, we conduct multi-source neural machine translation (NMT) models using the multilingual corpora such as string data corpus, tree data corpus, or POS-tagged data corpus. The multi-source translation is an approach to exploit multiple inputs (e.g. in two different formats) to increase translation accuracy. The RNN-based encoder-decoder model with attention mechanism and transformer architectures have been carried out for our experiment. The experimental results showed that the proposed models of RNN-based architecture outperform the baseline model for English-to-Myanmar translation task, and the multi-source and shared-multi-source transformer models yield better translation results than the baseline.
In this paper, we present the details of the systems that we have submitted for the WAT 2021 MultiIndicMT: An Indic Language Multilingual Task. We have submitted two separate multilingual NMT models: one for English to 10 Indic languages and another
for 10 Indic languages to English. We discuss the implementation details of two separate multilingual NMT approaches, namely one-to-many and many-to-one, that makes use of a shared decoder and a shared encoder, respectively. From our experiments, we observe that the multilingual NMT systems outperforms the bilingual baseline MT systems for each of the language pairs under consideration.
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 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.
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
