Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userReasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge
التفكير فوق الرؤية واللغة: استكشاف فوائد المعرفة الإضافية
167
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يتم تعريف حدود قابلية تطبيق نماذج الرؤية واللغة من خلال تغطية بياناتها التدريبية. تتطلب المهام مثل الرؤية الإجابة على الأسئلة (VQA) في كثير من الأحيان معلومات المنطقية والواقعية تتجاوز ما يمكن تعلمه من مجموعات البيانات الخاصة بمهام المهام. تحقق هذه الورقة في حقن المعرفة من قواعد المعرفة العامة للأغراض العامة (KBS) إلى محولات الرؤية واللغة. نحن نستخدم هدف تدريب إضافي يشجع التمثيلات المستفادة على محاذاة مع شرطة الرسم البياني للكيانات المطابقة في KB. ندرس تجريبيا أهمية مختلفة KBS إلى مهام ومعايير متعددة. توفر هذه التقنية فوائد واضحة لاستكشاف السؤال المطلقة على المعرفة (OK-VQA، FVQA) من خلال التقاط المعرفة الدلالية والعلدية غائبة عن النماذج القائمة. أكثر من المستغرب، فإن هذه التقنية تفيد أيضا مهام التفكير البصري (NLVR2، SNLI-VE). نقوم بإجراء تجارب التحقيق وإظهار أن حقن المعرفة الإضافية ينتقلان مساحة الشريات التي تحسن من تمثيل أوجه التشابه المعجمية والدلالية. تقنية النموذج الأذرع ويمكن أن توسع قابلية تطبيق أي محول للرؤية واللغة مع الحد الأدنى من النفقات الحاسوبية.
The limits of applicability of vision-and language models are defined by the coverage of their training data. Tasks like vision question answering (VQA) often require commonsense and factual information beyond what can be learned from task-specific datasets. This paper investigates the injection of knowledge from general-purpose knowledge bases (KBs) into vision-and-language transformers. We use an auxiliary training objective that encourages the learned representations to align with graph embeddings of matching entities in a KB. We empirically study the relevance of various KBs to multiple tasks and benchmarks. The technique brings clear benefits to knowledge-demanding question answering tasks (OK-VQA, FVQA) by capturing semantic and relational knowledge absent from existing models. More surprisingly, the technique also benefits visual reasoning tasks (NLVR2, SNLI-VE). We perform probing experiments and show that the injection of additional knowledge regularizes the space of embeddings, which improves the representation of lexical and semantic similarities. The technique is model-agnostic and can expand the applicability of any vision-and-language transformer with minimal computational overhead.
References used
https://aclanthology.org/
rate research
Read More
An exciting frontier in natural language understanding (NLU) and generation (NLG) calls for (vision-and-) language models that can efficiently access external structured knowledge repositories. However, many existing knowledge bases only cover limite
d domains, or suffer from noisy data, and most of all are typically hard to integrate into neural language pipelines. To fill this gap, we release VisualSem: a high-quality knowledge graph (KG) which includes nodes with multilingual glosses, multiple illustrative images, and visually relevant relations. We also release a neural multi-modal retrieval model that can use images or sentences as inputs and retrieves entities in the KG. This multi-modal retrieval model can be integrated into any (neural network) model pipeline. We encourage the research community to use VisualSem for data augmentation and/or as a source of grounding, among other possible uses. VisualSem as well as the multi-modal retrieval models are publicly available and can be downloaded in this URL: https://github.com/iacercalixto/visualsem.
Linguistic representations derived from text alone have been criticized for their lack of grounding, i.e., connecting words to their meanings in the physical world. Vision-and- Language (VL) models, trained jointly on text and image or video data, ha
ve been offered as a response to such criticisms. However, while VL pretraining has shown success on multimodal tasks such as visual question answering, it is not yet known how the internal linguistic representations themselves compare to their text-only counterparts. This paper compares the semantic representations learned via VL vs. text-only pretraining for two recent VL models using a suite of analyses (clustering, probing, and performance on a commonsense question answering task) in a language-only setting. We find that the multimodal models fail to significantly outperform the text-only variants, suggesting that future work is required if multimodal pretraining is to be pursued as a means of improving NLP in general.
Phrase grounding aims to map textual phrases to their associated image regions, which can be a prerequisite for multimodal reasoning and can benefit tasks requiring identifying objects based on language. With pre-trained vision-and-language models ac
hieving impressive performance across tasks, it remains unclear if we can directly utilize their learned embeddings for phrase grounding without fine-tuning. To this end, we propose a method to extract matched phrase-region pairs from pre-trained vision-and-language embeddings and propose four fine-tuning objectives to improve the model phrase grounding ability using image-caption data without any supervised grounding signals. Experiments on two representative datasets demonstrate the effectiveness of our objectives, outperforming baseline models in both weakly-supervised and supervised phrase grounding settings. In addition, we evaluate the aligned embeddings on several other downstream tasks and show that we can achieve better phrase grounding without sacrificing representation generality.
We propose the task of automatically generating commentaries for races in a motor racing game, from vision, structured numerical, and textual data. Commentaries provide information to support spectators in understanding events in races. Commentary ge
neration models need to interpret the race situation and generate the correct content at the right moment. We divide the task into two subtasks: utterance timing identification and utterance generation. Because existing datasets do not have such alignments of data in multiple modalities, this setting has not been explored in depth. In this study, we introduce a new large-scale dataset that contains aligned video data, structured numerical data, and transcribed commentaries that consist of 129,226 utterances in 1,389 races in a game. Our analysis reveals that the characteristics of commentaries change over time or from viewpoints. Our experiments on the subtasks show that it is still challenging for a state-of-the-art vision encoder to capture useful information from videos to generate accurate commentaries. We make the dataset and baseline implementation publicly available for further research.
Reasoning about tabular information presents unique challenges to modern NLP approaches which largely rely on pre-trained contextualized embeddings of text. In this paper, we study these challenges through the problem of tabular natural language infe
rence. We propose easy and effective modifications to how information is presented to a model for this task. We show via systematic experiments that these strategies substantially improve tabular inference performance.
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
