With recent progress in large-scale vision and language representation learning, Vision Language Pretraining (VLP) models have achieved promising improvements on various multi-modal downstream tasks. Albeit powerful, these pre-training models still do not take advantage of world knowledge, which is implicit in multi-modal data but comprises abundant and complementary information. In this work, we propose a REtrieval-based knowledge Augmented Vision Language Pre-training model (REAVL), which retrieves world knowledge from knowledge graphs (KGs) and incorporates them in vision-language pre-training. REAVL has two core components: a knowledge retriever that retrieves knowledge given multi-modal data, and a knowledge-augmented model that fuses multi-modal data and knowledge. By novelly unifying four knowledge-aware self-supervised tasks, REAVL promotes the mutual integration of multi-modal data and knowledge by fusing explicit knowledge with vision-language pairs for masked multi-modal data modeling and KG relational reasoning. Empirical experiments show that REAVL achieves new state-of-the-art performance uniformly on knowledge-based vision-language understanding and multimodal entity linking tasks, and competitive results on general vision-language tasks while only using 0.2% pre-training data of the best models.
相關內容
通過學習、實踐或探索所獲得的認識、判斷或技能。
Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from the pre-training dataset. Hence, a key ingredient to their success has been the use of large-scale curated pre-training data aiming at expanding the set of concepts that they can memorize during the pre-training stage. In this work, we explore an alternative to encoding fine-grained knowledge directly into the model's parameters: we instead train the model to retrieve this knowledge from an external memory. Specifically, we propose to equip existing vision-text models with the ability to refine their embedding with cross-modal retrieved information from a memory at inference time, which greatly improves their zero-shot predictions. Remarkably, we show that this can be done with a light-weight, single-layer, fusion transformer on top of a frozen CLIP. Our experiments validate that our retrieval-enhanced contrastive (RECO) training improves CLIP performance substantially on several challenging fine-grained tasks: for example +10.9 on Stanford Cars, +10.2 on CUB-2011 and +7.3 on the recent OVEN benchmark.
Language models retain a significant amount of world knowledge from their pre-training stage. This allows knowledgeable models to be applied to knowledge-intensive tasks prevalent in information retrieval, such as ranking or question answering. Understanding how and which factual information is acquired by our models is necessary to build responsible models. However, limited work has been done to understand the effect of pre-training tasks on the amount of knowledge captured and forgotten by language models during pre-training. Building a better understanding of knowledge acquisition is the goal of this paper. Therefore, we utilize a selection of pre-training tasks to infuse knowledge into our model. In the following steps, we test the model's knowledge retention by measuring its ability to answer factual questions. Our experiments show that masking entities and principled masking of correlated spans based on pointwise mutual information lead to more factual knowledge being retained than masking random tokens. Our findings demonstrate that, like the ability to perform a task, the (factual) knowledge acquired from being trained on that task is forgotten when a model is trained to perform another task (catastrophic forgetting) and how to prevent this phenomenon. To foster reproducibility, the code, as well as the data used in this paper, are openly available.
Cross-modal alignment plays a crucial role in vision-language pre-training (VLP) models, enabling them to capture meaningful associations across different modalities. For this purpose, inspired by the success of masked language modeling (MLM) tasks in the NLP pre-training area, numerous masked modeling tasks have been proposed for VLP to further promote cross-modal interactions. The core idea of previous masked modeling tasks is to focus on reconstructing the masked tokens based on visible context for learning local-local alignment, i.e., associations between image patches and text tokens. However, most of them pay little attention to the global semantic features generated for the masked data, resulting in a limited cross-modal alignment ability of global representations to local features of the other modality. Therefore, in this paper, we propose a novel Global and Local Semantic Completion Learning (GLSCL) task to facilitate global-local alignment and local-local alignment simultaneously. Specifically, the GLSCL task complements the missing semantics of masked data and recovers global and local features by cross-modal interactions. Our GLSCL consists of masked global semantic completion (MGSC) and masked local token completion (MLTC). MGSC promotes learning more representative global features which have a great impact on the performance of downstream tasks, and MLTC can further enhance accurate comprehension on multimodal data. Moreover, we present a flexible vision encoder, enabling our model to simultaneously perform image-text and video-text multimodal tasks. Experimental results show that our proposed method obtains state-of-the-art performance on various vision-language benchmarks, such as visual question answering, image-text retrieval, and video-text retrieval.
Knowledge tracing plays a pivotal role in intelligent tutoring systems. This task aims to predict the probability of students answering correctly to specific questions. To do so, knowledge tracing systems should trace the knowledge state of the students by utilizing their problem-solving history and knowledge about the problems. Recent advances in knowledge tracing models have enabled better exploitation of problem solving history. However, knowledge about problems has not been studied, as well compared to students' answering histories. Knowledge tracing algorithms that incorporate knowledge directly are important to settings with limited data or cold starts. Therefore, we consider the problem of utilizing skill-to-skill relation to knowledge tracing. In this work, we introduce expert labeled skill-to-skill relationships. Moreover, we also provide novel methods to construct a knowledge-tracing model to leverage human experts' insight regarding relationships between skills. The results of an extensive experimental analysis show that our method outperformed a baseline Transformer model. Furthermore, we found that the extent of our model's superiority was greater in situations with limited data, which allows a smooth cold start of our model.
There have been many recent investigations into prompt-based training of transformer language models for new text genres in low-resource settings. The prompt-based training approach has been found to be effective in generalizing pre-trained or fine-tuned models for transfer to resource-scarce settings. This work, for the first time, reports results on adopting prompt-based training of transformers for \textit{scholarly knowledge graph object prediction}. The work is unique in the following two main aspects. 1) It deviates from the other works proposing entity and relation extraction pipelines for predicting objects of a scholarly knowledge graph. 2) While other works have tested the method on text genera relatively close to the general knowledge domain, we test the method for a significantly different domain, i.e. scholarly knowledge, in turn testing the linguistic, probabilistic, and factual generalizability of these large-scale transformer models. We find that (i) per expectations, transformer models when tested out-of-the-box underperform on a new domain of data, (ii) prompt-based training of the models achieve performance boosts of up to 40\% in a relaxed evaluation setting, and (iii) testing the models on a starkly different domain even with a clever training objective in a low resource setting makes evident the domain knowledge capture gap offering an empirically-verified incentive for investing more attention and resources to the scholarly domain in the context of transformer models.
In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream uni-modal tasks and avoid training a new model from scratch. So can such pre-trained models be applied to multi-modal tasks? Researchers have explored this problem and made significant progress. This paper surveys recent advances and new frontiers in vision-language pre-training (VLP), including image-text and video-text pre-training. To give readers a better overall grasp of VLP, we first review its recent advances from five aspects: feature extraction, model architecture, pre-training objectives, pre-training datasets, and downstream tasks. Then, we summarize the specific VLP models in detail. Finally, we discuss the new frontiers in VLP. To the best of our knowledge, this is the first survey on VLP. We hope that this survey can shed light on future research in the VLP field.
Recently pre-trained language representation models such as BERT have shown great success when fine-tuned on downstream tasks including information retrieval (IR). However, pre-training objectives tailored for ad-hoc retrieval have not been well explored. In this paper, we propose Pre-training with Representative wOrds Prediction (PROP) for ad-hoc retrieval. PROP is inspired by the classical statistical language model for IR, specifically the query likelihood model, which assumes that the query is generated as the piece of text representative of the "ideal" document. Based on this idea, we construct the representative words prediction (ROP) task for pre-training. Given an input document, we sample a pair of word sets according to the document language model, where the set with higher likelihood is deemed as more representative of the document. We then pre-train the Transformer model to predict the pairwise preference between the two word sets, jointly with the Masked Language Model (MLM) objective. By further fine-tuning on a variety of representative downstream ad-hoc retrieval tasks, PROP achieves significant improvements over baselines without pre-training or with other pre-training methods. We also show that PROP can achieve exciting performance under both the zero- and low-resource IR settings. The code and pre-trained models are available at //github.com/Albert-Ma/PROP.
We propose a knowledge-enhanced approach, ERNIE-ViL, to learn joint representations of vision and language. ERNIE-ViL tries to construct the detailed semantic connections (objects, attributes of objects and relationships between objects in visual scenes) across vision and language, which are essential to vision-language cross-modal tasks. Incorporating knowledge from scene graphs, ERNIE-ViL constructs Scene Graph Prediction tasks, i.e., Object Prediction, Attribute Prediction and Relationship Prediction in the pre-training phase. More specifically, these prediction tasks are implemented by predicting nodes of different types in the scene graph parsed from the sentence. Thus, ERNIE-ViL can model the joint representation characterizing the alignments of the detailed semantics across vision and language. Pre-trained on two large image-text alignment datasets (Conceptual Captions and SBU), ERNIE-ViL learns better and more robust joint representations. It achieves state-of-the-art performance on 5 vision-language downstream tasks after fine-tuning ERNIE-ViL. Furthermore, it ranked the 1st place on the VCR leader-board with an absolute improvement of 3.7%.
State-of-the-art recommendation algorithms -- especially the collaborative filtering (CF) based approaches with shallow or deep models -- usually work with various unstructured information sources for recommendation, such as textual reviews, visual images, and various implicit or explicit feedbacks. Though structured knowledge bases were considered in content-based approaches, they have been largely neglected recently due to the availability of vast amount of data, and the learning power of many complex models. However, structured knowledge bases exhibit unique advantages in personalized recommendation systems. When the explicit knowledge about users and items is considered for recommendation, the system could provide highly customized recommendations based on users' historical behaviors. A great challenge for using knowledge bases for recommendation is how to integrated large-scale structured and unstructured data, while taking advantage of collaborative filtering for highly accurate performance. Recent achievements on knowledge base embedding sheds light on this problem, which makes it possible to learn user and item representations while preserving the structure of their relationship with external knowledge. In this work, we propose to reason over knowledge base embeddings for personalized recommendation. Specifically, we propose a knowledge base representation learning approach to embed heterogeneous entities for recommendation. Experimental results on real-world dataset verified the superior performance of our approach compared with state-of-the-art baselines.
Machine Learning has been the quintessential solution for many AI problems, but learning is still heavily dependent on the specific training data. Some learning models can be incorporated with a prior knowledge in the Bayesian set up, but these learning models do not have the ability to access any organised world knowledge on demand. In this work, we propose to enhance learning models with world knowledge in the form of Knowledge Graph (KG) fact triples for Natural Language Processing (NLP) tasks. Our aim is to develop a deep learning model that can extract relevant prior support facts from knowledge graphs depending on the task using attention mechanism. We introduce a convolution-based model for learning representations of knowledge graph entity and relation clusters in order to reduce the attention space. We show that the proposed method is highly scalable to the amount of prior information that has to be processed and can be applied to any generic NLP task. Using this method we show significant improvement in performance for text classification with News20, DBPedia datasets and natural language inference with Stanford Natural Language Inference (SNLI) dataset. We also demonstrate that a deep learning model can be trained well with substantially less amount of labeled training data, when it has access to organised world knowledge in the form of knowledge graph.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191