Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHow Vision Affects Language: Comparing Masked Self-Attention in Uni-Modal and Multi-Modal Transformer
كيف تؤثر الرؤية على اللغة: مقارنة اهتمامي عن النفس ملثمين في محول UNI-MODAL ومتعدد الوسائط
338
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
كانت مشكلة تفسير المعرفة المستفادة من قبل اهتمام ذاتي متعدد الأطراف في المحولات واحدة من الأسئلة المركزية في NLP. ومع ذلك، فإن الكثير من العمل يركز بشكل أساسي على النماذج المدربة لمهام UNI-MODAL، على سبيل المثال الترجمة الآلية. في هذه الورقة، نقوم بفحص اهتمامي عن نفسه في محول متعدد الوسائط مدربا لمهمة تقسيم الصور. على وجه الخصوص، نحن نختبر ما إذا كانت الوسيلة متعددة المهام تؤثر على أنماط الاهتمام المستفاد. أظهرت تصوراتنا المتمثلة في اهتمام ذاتي ملثمين أن المعرفة اللغوية العامة للمدخلات النصية، و (2) دمج أنماط اهتمامها من القطع الأثرية من طريقة مرئية على الرغم من أنها لم تصل إليها مباشرة. قارنا أنماط انتباه المحولات لدينا مع الاهتمام الملثمين في DistilGPT-2 تم اختباره لجيلي UNI-MODAL لنص التسميات التوضيحية للصور. بناء على خرائط أوزان الاهتمام المستخرجة، فإننا نجادل بأنه ملثم بالاهتمام الذاتي في محول تقسيم الصور يبدو أنه يعزز مع المعرفة الدلالية من الصور، مماثلة للحصول على معلومات مشتركة بين اللغة والرؤية في أنماط اهتمامها.
The problem of interpretation of knowledge learned by multi-head self-attention in transformers has been one of the central questions in NLP. However, a lot of work mainly focused on models trained for uni-modal tasks, e.g. machine translation. In this paper, we examine masked self-attention in a multi-modal transformer trained for the task of image captioning. In particular, we test whether the multi-modality of the task objective affects the learned attention patterns. Our visualisations of masked self-attention demonstrate that (i) it can learn general linguistic knowledge of the textual input, and (ii) its attention patterns incorporate artefacts from visual modality even though it has never accessed it directly. We compare our transformer's attention patterns with masked attention in distilgpt-2 tested for uni-modal text generation of image captions. Based on the maps of extracted attention weights, we argue that masked self-attention in image captioning transformer seems to be enhanced with semantic knowledge from images, exemplifying joint language-and-vision information in its attention patterns.
References used
https://aclanthology.org/
rate research
Read More
Vision language navigation is the task that requires an agent to navigate through a 3D environment based on natural language instructions. One key challenge in this task is to ground instructions with the current visual information that the agent per
ceives. Most of the existing work employs soft attention over individual words to locate the instruction required for the next action. However, different words have different functions in a sentence (e.g., modifiers convey attributes, verbs convey actions). Syntax information like dependencies and phrase structures can aid the agent to locate important parts of the instruction. Hence, in this paper, we propose a navigation agent that utilizes syntax information derived from a dependency tree to enhance alignment between the instruction and the current visual scenes. Empirically, our agent outperforms the baseline model that does not use syntax information on the Room-to-Room dataset, especially in the unseen environment. Besides, our agent achieves the new state-of-the-art on Room-Across-Room dataset, which contains instructions in 3 languages (English, Hindi, and Telugu). We also show that our agent is better at aligning instructions with the current visual information via qualitative visualizations.
Recent vision-language understanding approaches adopt a multi-modal transformer pre-training and finetuning paradigm. Prior work learns representations of text tokens and visual features with cross-attention mechanisms and captures the alignment sole
ly based on indirect signals. In this work, we propose to enhance the alignment mechanism by incorporating image scene graph structures as the bridge between the two modalities, and learning with new contrastive objectives. In our preliminary study on the challenging compositional visual question answering task, we show the proposed approach achieves improved results, demonstrating potentials to enhance vision-language understanding.
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.
Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In this paper,
we observe several key disadvantages of MLM in this setting. First, as captions tend to be short, in a third of the sentences no token is sampled. Second, the majority of masked tokens are stop-words and punctuation, leading to under-utilization of the image. We investigate a range of alternative masking strategies specific to the cross-modal setting that address these shortcomings, aiming for better fusion of text and image in the learned representation. When pre-training the LXMERT model, our alternative masking strategies consistently improve over the original masking strategy on three downstream tasks, especially in low resource settings. Further, our pre-training approach substantially outperforms the baseline model on a prompt-based probing task designed to elicit image objects. These results and our analysis indicate that our method allows for better utilization of the training data.
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
