In the Machine Learning research community, there is a consensus regarding the relationship between model complexity and the required amount of data and computation power. In real world applications, these computational requirements are not always available, motivating research on regularization methods. In addition, current and past research have shown that simpler classification algorithms can reach state-of-the-art performance on computer vision tasks given a robust method to artificially augment the training dataset. Because of this, data augmentation techniques became a popular research topic in recent years. However, existing data augmentation methods are generally less transferable than other regularization methods. In this paper we identify the main areas of application of data augmentation algorithms, the types of algorithms used, significant research trends, their progression over time and research gaps in data augmentation literature. To do this, the related literature was collected through the Scopus database. Its analysis was done following network science, text mining and exploratory analysis approaches. We expect readers to understand the potential of data augmentation, as well as identify future research directions and open questions within data augmentation research.
Pre-trained language models (PLMs) like BERT have made significant progress in various downstream NLP tasks. However, by asking models to do cloze-style tests, recent work finds that PLMs are short in acquiring knowledge from unstructured text. To understand the internal behaviour of PLMs in retrieving knowledge, we first define knowledge-baring (K-B) tokens and knowledge-free (K-F) tokens for unstructured text and ask professional annotators to label some samples manually. Then, we find that PLMs are more likely to give wrong predictions on K-B tokens and attend less attention to those tokens inside the self-attention module. Based on these observations, we develop two solutions to help the model learn more knowledge from unstructured text in a fully self-supervised manner. Experiments on knowledge-intensive tasks show the effectiveness of the proposed methods. To our best knowledge, we are the first to explore fully self-supervised learning of knowledge in continual pre-training.
Table-to-text generation refers to generating a descriptive text from a key-value table. Traditional autoregressive methods, though can generate text with high fluency, suffer from low coverage and poor faithfulness problems. To mitigate these problems, we propose a novel Skeleton-based two-stage method that combines both Autoregressive and Non-Autoregressive generations (SANA). Our approach includes: (1) skeleton generation with an autoregressive pointer network to select key tokens from the source table; (2) edit-based non-autoregressive generation model to produce texts via iterative insertion and deletion operations. By integrating hard constraints from the skeleton, the non-autoregressive model improves the generation's coverage over the source table and thus enhances its faithfulness. We conduct automatic and human evaluations on both WikiPerson and WikiBio datasets. Experimental results demonstrate that our method outperforms the previous state-of-the-art methods in both automatic and human evaluation, especially on coverage and faithfulness. In particular, we achieve PARENT-T recall of 99.47 in WikiPerson, improving over the existing best results by more than 10 points.
Informal mathematical text underpins real-world quantitative reasoning and communication. Developing sophisticated methods of retrieval and abstraction from this dual modality is crucial in the pursuit of the vision of automating discovery in quantitative science and mathematics. We track the development of informal mathematical language processing approaches across five strategic sub-areas in recent years, highlighting the prevailing successful methodological elements along with existing limitations.
Large-scale pretrained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language foundation model for both cross-modal understanding and generation. Most existing pre-trained models suffer from the problems of low computational efficiency and information asymmetry brought by the long visual sequence in cross-modal alignment. To address these problems, mPLUG introduces an effective and efficient vision-language architecture with novel cross-modal skip-connections, which creates inter-layer shortcuts that skip a certain number of layers for time-consuming full self-attention on the vision side. mPLUG is pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, such as image captioning, image-text retrieval, visual grounding and visual question answering. mPLUG also demonstrates strong zero-shot transferability when directly transferred to multiple video-language tasks.
In this paper, we propose DEXTER, an end to end system to extract information from tables present in medical health documents, such as electronic health records (EHR) and explanation of benefits (EOB). DEXTER consists of four sub-system stages: i) table detection ii) table type classification iii) cell detection; and iv) cell content extraction. We propose a two-stage transfer learning-based approach using CDeC-Net architecture along with Non-Maximal suppression for table detection. We design a conventional computer vision-based approach for table type classification and cell detection using parameterized kernels based on image size for detecting rows and columns. Finally, we extract the text from the detected cells using pre-existing OCR engine Tessaract. To evaluate our system, we manually annotated a sample of the real-world medical dataset (referred to as Meddata) consisting of wide variations of documents (in terms of appearance) covering different table structures, such as bordered, partially bordered, borderless, or coloured tables. We experimentally show that DEXTER outperforms the commercially available Amazon Textract and Microsoft Azure Form Recognizer systems on the annotated real-world medical dataset
Large text-guided diffusion models, such as DALLE-2, are able to generate stunning photorealistic images given natural language descriptions. While such models are highly flexible, they struggle to understand the composition of certain concepts, such as confusing the attributes of different objects or relations between objects. In this paper, we propose an alternative structured approach for compositional generation using diffusion models. An image is generated by composing a set of diffusion models, with each of them modeling a certain component of the image. To do this, we interpret diffusion models as energy-based models in which the data distributions defined by the energy functions may be explicitly combined. The proposed method can generate scenes at test time that are substantially more complex than those seen in training, composing sentence descriptions, object relations, human facial attributes, and even generalizing to new combinations that are rarely seen in the real world. We further illustrate how our approach may be used to compose pre-trained text-guided diffusion models and generate photorealistic images containing all the details described in the input descriptions, including the binding of certain object attributes that have been shown difficult for DALLE-2. These results point to the effectiveness of the proposed method in promoting structured generalization for visual generation. Project page: https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/
The application of zero-shot learning in computer vision has been revolutionized by the use of image-text matching models. The most notable example, CLIP, has been widely used for both zero-shot classification and guiding generative models with a text prompt. However, the zero-shot use of CLIP is unstable with respect to the phrasing of the input text, making it necessary to carefully engineer the prompts used. We find that this instability stems from a selective similarity score, which is based only on a subset of the semantically meaningful input tokens. To mitigate it, we present a novel explainability-based approach, which adds a loss term to ensure that CLIP focuses on all relevant semantic parts of the input, in addition to employing the CLIP similarity loss used in previous works. When applied to one-shot classification through prompt engineering, our method yields an improvement in the recognition rate, without additional training or fine-tuning. Additionally, we show that CLIP guidance of generative models using our method significantly improves the generated images. Finally, we demonstrate a novel use of CLIP guidance for text-based image generation with spatial conditioning on object location, by requiring the image explainability heatmap for each object to be confined to a pre-determined bounding box.
Starting from 2021, the International Maritime Organization significantly tightened the $\text{NO}_\text{x}$ emission requirements for ships entering the Baltic and North Sea waters. Since all methods currently used for the ships' compliance monitoring are costly and require proximity to the ship, the performance of a global and continuous monitoring of the emission standards' fulfillment has been impossible up to now. A promising approach is the use of remote sensing with the recently launched TROPOMI/S5P satellite. Due to its unprecedentedly high spatial resolution, it allows for the visual distinction of $\text{NO}_\text{2}$ plumes of individual ships. To successfully deploy a compliance monitoring system that is based on TROPOMI data, an automated procedure for the attribution of $\text{NO}_\text{2}$ to individual ships has to be developed. However, due to the extremely low signal-to-noise ratio, interference with the signal from other - often stronger - sources, and the absence of ground truth, the task is very challenging. In this study, we present an automated method for segmentation of plumes produced by individual ships using TROPOMI satellite data - a first step towards the automated procedure for global ship compliance monitoring. We develop a multivariate plume segmentation method based on various ships', wind's and spatial properties. For this, we propose to automatically define a region of interest - a ship sector that we normalize with respect to scale and orientation. We create a dataset, where each pixel has a label for belonging to the respective ship plume or not. We train five linear and nonlinear classifiers. The results show a significant improvement over the threshold-based baselines. Moreover, the aggregated $\text{NO}_\text{2}$ levels of the segmented plumes show high correlation with the theoretically derived measure of ship's emission potential.
Contrastive Learning has emerged as a powerful representation learning method and facilitates various downstream tasks especially when supervised data is limited. How to construct efficient contrastive samples through data augmentation is key to its success. Unlike vision tasks, the data augmentation method for contrastive learning has not been investigated sufficiently in language tasks. In this paper, we propose a novel approach to constructing contrastive samples for language tasks using text summarization. We use these samples for supervised contrastive learning to gain better text representations which greatly benefit text classification tasks with limited annotations. To further improve the method, we mix up samples from different classes and add an extra regularization, named mix-sum regularization, in addition to the cross-entropy-loss. Experiments on real-world text classification datasets (Amazon-5, Yelp-5, AG News) demonstrate the effectiveness of the proposed contrastive learning framework with summarization-based data augmentation and mix-sum regularization.