Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userExperiences of Adapting Multimodal Machine Translation Techniques for Hindi
تجارب تكييف تقنيات الترجمة المتعددة الوسائط للهيكلية
348
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
الترجمة الآلية العصبية متعددة الوسائط (MNMT) هي مهمة مثيرة للاهتمام في معالجة اللغة الطبيعية (NLP) حيث نستخدم طرائق مرئية إلى جانب جملة مصدر لمساعدة المصدر لعملية الترجمة المستهدفة.في الآونة الأخيرة، كان هناك الكثير من الأعمال في أطر MNMT لتعزيز أداء مهام الترجمة ذات الجهاز المستقل.حاولت معظم الأعمال السابقة في MNMT إجراء الترجمة بين لغتان معروفتين على نطاق واسع (على سبيل المثال English-to-German، الإنجليزية إلى الفرنسية).في هذه الورقة، نستكشف فعالية أساليب MNMT المختلفة، والتي تستخدم تقنيات مختلفة الموجهة نحو البيانات بما في ذلك التدريب المسبق متعدد الوسائط، لغات موارد منخفضة.على الرغم من أن الأساليب الحالية تعمل بشكل جيد على لغات الموارد العالية، إلا أن قابلية استخدام تلك الأساليب على لغات الموارد المنخفضة غير معروفة.في هذه الورقة، نقيم الطرق الحالية على الهندية والإبلاغ عن نتائجنا.
Multimodal Neural Machine Translation (MNMT) is an interesting task in natural language processing (NLP) where we use visual modalities along with a source sentence to aid the source to target translation process. Recently, there has been a lot of works in MNMT frameworks to boost the performance of standalone Machine Translation tasks. Most of the prior works in MNMT tried to perform translation between two widely known languages (e.g. English-to-German, English-to-French ). In this paper, We explore the effectiveness of different state-of-the-art MNMT methods, which use various data oriented techniques including multimodal pre-training, for low resource languages. Although the existing methods works well on high resource languages, usability of those methods on low-resource languages is unknown. In this paper, we evaluate the existing methods on Hindi and report our findings.
References used
https://aclanthology.org/
rate research
Read More
Machine translation performs automatic translation from one natural language to another. Neural machine translation attains a state-of-the-art approach in machine translation, but it requires adequate training data, which is a severe problem for low-
resource language pairs translation. The concept of multimodal is introduced in neural machine translation (NMT) by merging textual features with visual features to improve low-resource pair translation. WAT2021 (Workshop on Asian Translation 2021) organizes a shared task of multimodal translation for English to Hindi. We have participated the same with team name CNLP-NITS-PP in two submissions: multimodal and text-only NMT. This work investigates phrase pairs injection via data augmentation approach and attains improvement over our previous work at WAT2020 on the same task in both text-only and multimodal NMT. We have achieved second rank on the challenge test set for English to Hindi multimodal translation where Bilingual Evaluation Understudy (BLEU) score of 39.28, Rank-based Intuitive Bilingual Evaluation Score (RIBES) 0.792097, and Adequacy-Fluency Metrics (AMFM) score 0.830230 respectively.
Automatic post-editing (APE) models are usedto correct machine translation (MT) system outputs by learning from human post-editing patterns. We present the system used in our submission to the WMT'21 Automatic Post-Editing (APE) English-German (En-De
) shared task. We leverage the state-of-the-art MT system (Ng et al., 2019) for this task. For further improvements, we adapt the MT model to the task domain by using WikiMatrix (Schwenket al., 2021) followed by fine-tuning with additional APE samples from previous editions of the shared task (WMT-16,17,18) and ensembling the models. Our systems beat the baseline on TER scores on the WMT'21 test set.
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.
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.
We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series of experime
nts through fine-tuning a translation model on data where either the source or target language has changed. These experiments reveal that fine-tuning only the cross-attention parameters is nearly as effective as fine-tuning all parameters (i.e., the entire translation model). We provide insights into why this is the case and observe that limiting fine-tuning in this manner yields cross-lingually aligned embeddings. The implications of this finding for researchers and practitioners include a mitigation of catastrophic forgetting, the potential for zero-shot translation, and the ability to extend machine translation models to several new language pairs with reduced parameter storage overhead.
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
