Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEntity-level Cross-modal Learning Improves Multi-modal Machine Translation
مستوى التعليم عبر مستوى الكيان يحسن الترجمة متعددة الوسائط
248
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تهدف الترجمة متعددة الوسائط (MMT) إلى تحسين أداء الترجمة من خلال دمج المعلومات المرئية. معظم الدراسات الاستفادة من المعلومات المرئية من خلال دمج ميزات الصورة العالمية كمدخل إضافي أو فك تشفير من خلال حضور المناطق المحلية ذات الصلة في الصورة. ومع ذلك، فإن هذا النوع من استخدام المعلومات المرئية يجعل من الصعب معرفة كيفية تساعد طريقة المرئية ولماذا يعمل. مستوحاة من نتائج (الاقتباس) التي تعد الكيانات أكثر تفكيا في الصورة، نقترح نهجا للتعلم الصريح عبر مستوى الكيانات يهدف إلى زيادة تمثيل الكيان. على وجه التحديد، يتم تأطير النهج كهجوم لإعادة الإعمار الذي يعيد إدخال المدخلات النصية الأصلية من المدخلات متعددة الوسائط يتم استبدال الكيانات بالكيانات بالميزات المرئية. بعد ذلك، يتم استخدام إطار عمل متعدد المهام في الجمع بين مهمة الترجمة ومهمة إعادة الإعمار للاستفادة الكاملة من تعلم تمثيل الكيان عبر الوسائط. تثبت التجارب الواسعة أن نهجنا يمكن أن يحقق أداء قابلا للمقارنة أو أفضل من النماذج الحديثة. علاوة على ذلك، يوضح تحليلنا المتعمق كيفية تحسين المعلومات المرئية الترجمة.
Multi-modal machine translation (MMT) aims at improving translation performance by incorporating visual information. Most of the studies leverage the visual information through integrating the global image features as auxiliary input or decoding by attending to relevant local regions of the image. However, this kind of usage of visual information makes it difficult to figure out how the visual modality helps and why it works. Inspired by the findings of (CITATION) that entities are most informative in the image, we propose an explicit entity-level cross-modal learning approach that aims to augment the entity representation. Specifically, the approach is framed as a reconstruction task that reconstructs the original textural input from multi-modal input in which entities are replaced with visual features. Then, a multi-task framework is employed to combine the translation task and the reconstruction task to make full use of cross-modal entity representation learning. The extensive experiments demonstrate that our approach can achieve comparable or even better performance than state-of-the-art models. Furthermore, our in-depth analysis shows how visual information improves translation.
References used
https://aclanthology.org/
rate research
Read More
Neural machine translation based on bilingual text with limited training data suffers from lexical diversity, which lowers the rare word translation accuracy and reduces the generalizability of the translation system. In this work, we utilise the mul
tiple captions from the Multi-30K dataset to increase the lexical diversity aided with the cross-lingual transfer of information among the languages in a multilingual setup. In this multilingual and multimodal setting, the inclusion of the visual features boosts the translation quality by a significant margin. Empirical study affirms that our proposed multimodal approach achieves substantial gain in terms of the automatic score and shows robustness in handling the rare word translation in the pretext of English to/from Hindi and Telugu translation tasks.
Aspect terms extraction (ATE) and aspect sentiment classification (ASC) are two fundamental and fine-grained sub-tasks in aspect-level sentiment analysis (ALSA). In the textual analysis, joint extracting both aspect terms and sentiment polarities has
been drawn much attention due to the better applications than individual sub-task. However, in the multi-modal scenario, the existing studies are limited to handle each sub-task independently, which fails to model the innate connection between the above two objectives and ignores the better applications. Therefore, in this paper, we are the first to jointly perform multi-modal ATE (MATE) and multi-modal ASC (MASC), and we propose a multi-modal joint learning approach with auxiliary cross-modal relation detection for multi-modal aspect-level sentiment analysis (MALSA). Specifically, we first build an auxiliary text-image relation detection module to control the proper exploitation of visual information. Second, we adopt the hierarchical framework to bridge the multi-modal connection between MATE and MASC, as well as separately visual guiding for each sub module. Finally, we can obtain all aspect-level sentiment polarities dependent on the jointly extracted specific aspects. Extensive experiments show the effectiveness of our approach against the joint textual approaches, pipeline and collapsed multi-modal approaches.
Recent advances in using retrieval components over external knowledge sources have shown impressive results for a variety of downstream tasks in natural language processing. Here, we explore the use of unstructured external knowledge sources of image
s and their corresponding captions for improving visual question answering (VQA). First, we train a novel alignment model for embedding images and captions in the same space, which achieves substantial improvement in performance on image-caption retrieval w.r.t. similar methods. Second, we show that retrieval-augmented multi-modal transformers using the trained alignment model improve results on VQA over strong baselines. We further conduct extensive experiments to establish the promise of this approach, and examine novel applications for inference time such as hot-swapping indices.
We investigate the representations learned by vision and language models in tasks that require relational reasoning. Focusing on the problem of assessing the relative size of objects in abstract visual contexts, we analyse both one-step and two-step
reasoning. For the latter, we construct a new dataset of three-image scenes and define a task that requires reasoning at the level of the individual images and across images in a scene. We probe the learned model representations using diagnostic classifiers. Our experiments show that pretrained multimodal transformer-based architectures can perform higher-level relational reasoning, and are able to learn representations for novel tasks and data that are very different from what was seen in pretraining.
Document-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information. Nevertheless, existing approaches 1) simply introduce the representations of context sentences without expli
citly characterizing the inter-sentence reasoning process; and 2) feed ground-truth target contexts as extra inputs at the training time, thus facing the problem of exposure bias. We approach these problems with an inspiration from human behavior -- human translators ordinarily emerge a translation draft in their mind and progressively revise it according to the reasoning in discourse. To this end, we propose a novel Multi-Hop Transformer (MHT) which offers NMT abilities to explicitly model the human-like draft-editing and reasoning process. Specifically, our model serves the sentence-level translation as a draft and properly refines its representations by attending to multiple antecedent sentences iteratively. Experiments on four widely used document translation tasks demonstrate that our method can significantly improve document-level translation performance and can tackle discourse phenomena, such as coreference error and the problem of polysemy.
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
