Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userViTA: Visual-Linguistic Translation by Aligning Object Tags
VITA: الترجمة البصرية اللغوية عن طريق محاذاة علامات كائن
94
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
ترجمة آلة متعددة الوسائط (MMT) تثري النص المصدر بمعلومات مرئية للترجمة.لقد اكتسبت شعبية في السنوات الأخيرة، وقد اقترح العديد من خطوط الأنابيب في نفس الاتجاه.ومع ذلك، تفتقر المهمة إلى مجموعات بيانات الجودة لتوضيح مساهمة الوسيلة البصرية في أنظمة الترجمة.في هذه الورقة، نقترح نظامنا تحت اسم الفريق فولتا لمهمة الترجمة متعددة الوسائط في WAT 2021 من الإنجليزية إلى الهندية.نشارك أيضا في التراكب الفرعي النصي فقط لنفس زوج اللغة التي نستخدمها MBART، وهي نموذج تسلسل متعدد اللغات مسبقا.بالنسبة للترجمة متعددة الوسائط، نقترح تعزيز المدخلات النصية من خلال إحضار المعلومات المرئية إلى مجال نصي عن طريق استخراج علامات الكائنات من الصورة.نستكشف أيضا متانة نظامنا عن طريق مهينة النص المصدر بشكل منهجي.أخيرا، نحقق درجة بلو من 44.6 و 51.6 في مجموعة الاختبار ومجموعة التحدي بمهمة متعددة الوسائط.
Multimodal Machine Translation (MMT) enriches the source text with visual information for translation. It has gained popularity in recent years, and several pipelines have been proposed in the same direction. Yet, the task lacks quality datasets to illustrate the contribution of visual modality in the translation systems. In this paper, we propose our system under the team name Volta for the Multimodal Translation Task of WAT 2021 from English to Hindi. We also participate in the textual-only subtask of the same language pair for which we use mBART, a pretrained multilingual sequence-to-sequence model. For multimodal translation, we propose to enhance the textual input by bringing the visual information to a textual domain by extracting object tags from the image. We also explore the robustness of our system by systematically degrading the source text. Finally, we achieve a BLEU score of 44.6 and 51.6 on the test set and challenge set of the multimodal task.
References used
https://aclanthology.org/
rate research
Read More
Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often produce low
quality translations -- commonly failing to even produce outputs in the right target language. In this work, we observe that off-target translation is dominant even in strong multilingual systems, trained on massive multilingual corpora. To address this issue, we propose a joint approach to regularize NMT models at both representation-level and gradient-level. At the representation level, we leverage an auxiliary target language prediction task to regularize decoder outputs to retain information about the target language. At the gradient level, we leverage a small amount of direct data (in thousands of sentence pairs) to regularize model gradients. Our results demonstrate that our approach is highly effective in both reducing off-target translation occurrences and improving zero-shot translation performance by +5.59 and +10.38 BLEU on WMT and OPUS datasets respectively. Moreover, experiments show that our method also works well when the small amount of direct data is not available.
In this paper, we show that automatically-generated questions and answers can be used to evaluate the quality of Machine Translation (MT) systems. Building on recent work on the evaluation of abstractive text summarization, we propose a new metric for system-level MT evaluation, compare it with other state-of-the-art solutions, and show its robustness by conducting experiments for various MT directions.
Existing approaches for machine translation (MT) mostly translate given text in the source language into the target language and without explicitly referring to information indispensable for producing proper translation. This includes not only inform
ation in other textual elements and modalities than texts in the same document and but also extra-document and non-linguistic information and such as norms and skopos. To design better translation production work-flows and we need to distinguish translation issues that could be resolved by the existing text-to-text approaches and those beyond them. To this end and we conducted an analytic assessment of MT outputs and taking an English-to-Japanese news translation task as a case study. First and examples of translation issues and their revisions were collected by a two-stage post-editing (PE) method: performing minimal PE to obtain translation attainable based on the given textual information and further performing full PE to obtain truly acceptable translation referring to any information if necessary. Then and the collected revision examples were manually analyzed. We revealed dominant issues and information indispensable for resolving them and such as fine-grained style specifications and terminology and domain-specific knowledge and and reference documents and delineating a clear distinction between translation and what text-to-text MT can ultimately attain.
Recipe texts are an idiosyncratic form of instructional language that pose unique challenges for automatic understanding. One challenge is that a cooking step in one recipe can be explained in another recipe in different words, at a different level o
f abstraction, or not at all. Previous work has annotated correspondences between recipe instructions at the sentence level, often glossing over important correspondences between cooking steps across recipes. We present a novel and fully-parsed English recipe corpus, ARA (Aligned Recipe Actions), which annotates correspondences between individual actions across similar recipes with the goal of capturing information implicit for accurate recipe understanding. We represent this information in the form of recipe graphs, and we train a neural model for predicting correspondences on ARA. We find that substantial gains in accuracy can be obtained by taking fine-grained structural information about the recipes into account.
Abstract We find that the requirement of model interpretations to be faithful is vague and incomplete. With interpretation by textual highlights as a case study, we present several failure cases. Borrowing concepts from social science, we identify th
at the problem is a misalignment between the causal chain of decisions (causal attribution) and the attribution of human behavior to the interpretation (social attribution). We reformulate faithfulness as an accurate attribution of causality to the model, and introduce the concept of aligned faithfulness: faithful causal chains that are aligned with their expected social behavior. The two steps of causal attribution and social attribution together complete the process of explaining behavior. With this formalization, we characterize various failures of misaligned faithful highlight interpretations, and propose an alternative causal chain to remedy the issues. Finally, we implement highlight explanations of the proposed causal format using contrastive explanations.
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
