Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNLPHut's Participation at WAT2021
مشاركة NLPHUT في WAT2021
46
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
توفر هذه الورقة وصف المهام المشتركة مع WAT 2021 من قبل فريق NLPHUT الخاص بنا ".لقد شاركنا في اللغة الإنجليزية → Hindi Multimodal مهمة الترجمة، الإنجليزية → مهمة ترجمة Malayalam Multimodal، ومهمة الترجمة متعددة اللغات.لقد استخدمنا طراز المحولات الحديثة مع علامات اللغة في إعدادات مختلفة لمهمة الترجمة واقترح نهج تواتر التسمية التوضيحية الخاص بالمنطقة الرواية باستخدام مزيج من صورة CNN و LSTM للحصول على تقسيم الصور الهندية والمالياالاميةوبعدقمم التقديم لدينا باللغة الإنجليزية → Malayalam مهمة ترجمة متعددة الوسائط (ترجمة نصية فقط، ومالياالام التسمية التوضيحية)، وتحتل المرتبة الثانية في اللغة الإنجليزية → Hindi Multimodal Tasony Task (ترجمة النص فقط، والتسمية التوضيحية الهندية).كما أجرت عمليات التقديمات لدينا بشكل جيد في مهام الترجمة متعددة اللغات.
This paper provides the description of shared tasks to the WAT 2021 by our team NLPHut''. We have participated in the English→Hindi Multimodal translation task, English→Malayalam Multimodal translation task, and Indic Multi-lingual translation task. We have used the state-of-the-art Transformer model with language tags in different settings for the translation task and proposed a novel region-specific'' caption generation approach using a combination of image CNN and LSTM for the Hindi and Malayalam image captioning. Our submission tops in English→Malayalam Multimodal translation task (text-only translation, and Malayalam caption), and ranks second-best in English→Hindi Multimodal translation task (text-only translation, and Hindi caption). Our submissions have also performed well in the Indic Multilingual translation tasks.
References used
https://aclanthology.org/
rate research
Read More
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 subwor
d 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.
We introduce our TMEKU system submitted to the English-Japanese Multimodal Translation Task for WAT 2021. We participated in the Flickr30kEnt-JP task and Ambiguous MSCOCO Multimodal task under the constrained condition using only the officially provi
ded datasets. Our proposed system employs soft alignment of word-region for multimodal neural machine translation (MNMT). The experimental results evaluated on the BLEU metric provided by the WAT 2021 evaluation site show that the TMEKU system has achieved the best performance among all the participated systems. Further analysis of the case study demonstrates that leveraging word-region alignment between the textual and visual modalities is the key to performance enhancement in our TMEKU system, which leads to better visual information use.
This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task. We participated in all of the three sub-tasks, including Sentence-Level Direct Assessment (DA) task, Word and Sentence-Level Post-editing Effort task and Critical Error Det
ection task, in all language pairs. Our systems employ the framework of Predictor-Estimator, concretely with a pre-trained XLM-Roberta as Predictor and task-specific classifier or regressor as Estimator. For all tasks, we improve our systems by incorporating post-edit sentence or additional high-quality translation sentence in the way of multitask learning or encoding it with predictors directly. Moreover, in zero-shot setting, our data augmentation strategy based on Monte-Carlo Dropout brings up significant improvement on DA sub-task. Notably, our submissions achieve remarkable results over all tasks.
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.
This paper describes Lingua Custodia's submission to the WMT21 shared task on machine translation using terminologies. We consider three directions, namely English to French, Russian, and Chinese. We rely on a Transformer-based architecture as a buil
ding block, and we explore a method which introduces two main changes to the standard procedure to handle terminologies. The first one consists in augmenting the training data in such a way as to encourage the model to learn a copy behavior when it encounters terminology constraint terms. The second change is constraint token masking, whose purpose is to ease copy behavior learning and to improve model generalization. Empirical results show that our method satisfies most terminology constraints while maintaining high translation quality.
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
