Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBering Lab's Submissions on WAT 2021 Shared Task
تقارير Bering Lab في مهمة مشتركة WAT 2021
410
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقدم هذه الورقة تقديم مختبر Bering إلى المهام المشتركة للورشة الثامنة حول الترجمة الآسيوية (WAT 2021) على JPC2 و SAP.شاركنا في جميع المهام على JPC2 ومهام مجال تكنولوجيا المعلومات على NICT-SAP.نهجنا لجميع المهام يركز بشكل أساسي على بناء أنظمة NMT في كورسا خاصة بالمجال.لقد زحفنا أزواج وثيقة براءات الاختراع للغة الإنجليزية اليابانية والصينية اليابانية والكورية واليابانية.بعد تنظيف البيانات الصاخبة، بنينا كوربا متوازيا عن طريق مواءمة هذه الجمل مع درجات التشابه على مستوى الجملة.أيضا، للحصول على بيانات اختبار SAP، جمعنا مجموعة بيانات OPUS بما في ذلك ثلاثة كورسور كورسا.ثم تدريب محول على مجموعة البيانات التي تم جمعها.احتل إرسالنا في المرتبة الأولى في ثمانية من أربعة عشر مهام، وتحقيق ما يصل إلى تحسين 2.87 ل JPC2 و 8.79 ل SAP NIST-SAP في النتيجة بلو.
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 focused 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 .
References used
https://aclanthology.org/
rate research
Read More
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 presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task. We participate in the Russian-to-Chinese task under the constrained condition. We use Transformer architecture and obtain the best
performance via a variant with larger parameter sizes. We perform detailed data pre-processing and filtering on the provided large-scale bilingual data. Several strategies are used to train our models, such as Multilingual Translation, Back Translation, Forward Translation, Data Denoising, Average Checkpoint, Ensemble, Fine-tuning, etc. Our system obtains 32.5 BLEU on the dev set and 27.7 BLEU on the test set, the highest score among all submissions.
We describe the DCU-EPFL submission to the IWPT 2021 Parsing Shared Task: From Raw Text to Enhanced Universal Dependencies. The task involves parsing Enhanced UD graphs, which are an extension of the basic dependency trees designed to be more facilit
ative towards representing semantic structure. Evaluation is carried out on 29 treebanks in 17 languages and participants are required to parse the data from each language starting from raw strings. Our approach uses the Stanza pipeline to preprocess the text files, XLM-RoBERTa to obtain contextualized token representations, and an edge-scoring and labeling model to predict the enhanced graph. Finally, we run a postprocessing script to ensure all of our outputs are valid Enhanced UD graphs. Our system places 6th out of 9 participants with a coarse Enhanced Labeled Attachment Score (ELAS) of 83.57. We carry out additional post-deadline experiments which include using Trankit for pre-processing, XLM-RoBERTa LARGE, treebank concatenation, and multitask learning between a basic and an enhanced dependency parser. All of these modifications improve our initial score and our final system has a coarse ELAS of 88.04.
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.
The paper describes the 3 NMT models submitted by the eTranslation team to the WMT 2021 news translation shared task. We developed systems in language pairs that are actively used in the European Commission's eTranslation service. In the WMT news tas
k, recent years have seen a steady increase in the need for computational resources to train deep and complex architectures to produce competitive systems. We took a different approach and explored alternative strategies focusing on data selection and filtering to improve the performance of baseline systems. In the domain constrained task for the French--German language pair our approach resulted in the best system by a significant margin in BLEU. For the other two systems (English--German and English-Czech) we tried to build competitive models using standard best practices.
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
