With the overwhelming transition to smart phones, storing important information in the form of unstructured text has become habitual to users of mobile devices. From grocery lists to drafts of emails and important speeches, users store a lot of data in the form of unstructured text (for eg: in the Notes application) on their devices, leading to cluttering of data. This not only prevents users from efficient navigation in the applications but also precludes them from perceiving the relations that could be present across data in those applications. This paper proposes a novel pipeline to generate a set of tags using world knowledge based on the keywords and concepts present in unstructured textual data. These tags can then be used to summarize, categorize or search for the desired information thus enhancing user experience by allowing them to have a holistic outlook of the kind of information stored in the form of unstructured text. In the proposed system, we use an on-device (mobile phone) efficient CNN model with pruned ConceptNet resource to achieve our goal. The architecture also presents a novel ranking algorithm to extract the top n tags from any given text.
This paper addresses the problem of document image dewarping, which aims at eliminating the geometric distortion in document images for document digitization. Instead of designing a better neural network to approximate the optical flow fields between the inputs and outputs, we pursue the best readability by taking the text lines and the document boundaries into account from a constrained optimization perspective. Specifically, our proposed method first learns the boundary points and the pixels in the text lines and then follows the most simple observation that the boundaries and text lines in both horizontal and vertical directions should be kept after dewarping to introduce a novel grid regularization scheme. To obtain the final forward mapping for dewarping, we solve an optimization problem with our proposed grid regularization. The experiments comprehensively demonstrate that our proposed approach outperforms the prior arts by large margins in terms of readability (with the metrics of Character Errors Rate and the Edit Distance) while maintaining the best image quality on the publicly-available DocUNet benchmark.
Self-attention mechanisms model long-range context by using pairwise attention between all input tokens. In doing so, they assume a fixed attention granularity defined by the individual tokens (e.g., text characters or image pixels), which may not be optimal for modeling complex dependencies at higher levels. In this paper, we propose ContextPool to address this problem by adapting the attention granularity for each token. Inspired by the success of ConvNets that are combined with pooling to capture long-range dependencies, we learn to pool neighboring features for each token before computing attention in a given attention layer. The pooling weights and support size are adaptively determined, allowing the pooled features to encode meaningful context with varying scale. We show that ContextPool makes attention models more expressive, achieving strong performance often with fewer layers and thus significantly reduced cost. Experiments validate that our ContextPool module, when plugged into transformer models, matches or surpasses state-of-the-art performance using less compute on several language and image benchmarks, outperforms recent works with learned context sizes or sparse attention patterns, and is also applicable to ConvNets for efficient feature learning.
We present a generic and trend-aware curriculum learning approach for graph neural networks. It extends existing approaches by incorporating sample-level loss trends to better discriminate easier from harder samples and schedule them for training. The model effectively integrates textual and structural information for relation extraction in text graphs. Experimental results show that the model provides robust estimations of sample difficulty and shows sizable improvement over the state-of-the-art approaches across several datasets.
Text retrieval is often formulated as mapping the query and the target items (e.g., passages) to the same vector space and finding the item whose embedding is closest to that of the query. In this paper, we explore a generative approach as an alternative, where we use an encoder-decoder model to memorize the target corpus in a generative manner and then finetune it on query-to-passage generation. As GENRE(Cao et al., 2021) has shown that entities can be retrieved in a generative way, our work can be considered as its generalization to longer text. We show that it consistently achieves comparable performance to traditional bi-encoder retrieval on diverse datasets and is especially strong at retrieving highly structured items, such as reasoning chains and graph relations, while demonstrating superior GPU memory and time complexity. We also conjecture that generative retrieval is complementary to traditional retrieval, as we find that an ensemble of both outperforms homogeneous ensembles.
Among ubiquitous multimodal data in the real world, text is the modality generated by human, while image reflects the physical world honestly. In a visual understanding application, machines are expected to understand images like human. Inspired by this, we propose a novel self-supervised learning method, named Text-enhanced Visual Deep InfoMax (TVDIM), to learn better visual representations by fully utilizing the naturally-existing multimodal data. Our core idea of self-supervised learning is to maximize the mutual information between features extracted from multiple views of a shared context to a rational degree. Different from previous methods which only consider multiple views from a single modality, our work produces multiple views from different modalities, and jointly optimizes the mutual information for features pairs of intra-modality and inter-modality. Considering the information gap between inter-modality features pairs from data noise, we adopt a \emph{ranking-based} contrastive learning to optimize the mutual information. During evaluation, we directly use the pre-trained visual representations to complete various image classification tasks. Experimental results show that, TVDIM significantly outperforms previous visual self-supervised methods when processing the same set of images.
Environmental, Social, and Governance (ESG) are non-financial factors that are garnering attention from investors as they increasingly look to apply these as part of their analysis to identify material risks and growth opportunities. Some of this attention is also driven by clients who, now more aware than ever, are demanding for their money to be managed and invested responsibly. As the interest in ESG grows, so does the need for investors to have access to consumable ESG information. Since most of it is in text form in reports, disclosures, press releases, and 10-Q filings, we see a need for sophisticated NLP techniques for classification tasks for ESG text. We hypothesize that an ESG domain-specific pre-trained model will help with such and study building of the same in this paper. We explored doing this by fine-tuning BERTs pre-trained weights using ESG specific text and then further fine-tuning the model for a classification task. We were able to achieve accuracy better than the original BERT and baseline models in environment-specific classification tasks.
The recent state of the art on monocular 3D face reconstruction from image data has made some impressive advancements, thanks to the advent of Deep Learning. However, it has mostly focused on input coming from a single RGB image, overlooking the following important factors: a) Nowadays, the vast majority of facial image data of interest do not originate from single images but rather from videos, which contain rich dynamic information. b) Furthermore, these videos typically capture individuals in some form of verbal communication (public talks, teleconferences, audiovisual human-computer interactions, interviews, monologues/dialogues in movies, etc). When existing 3D face reconstruction methods are applied in such videos, the artifacts in the reconstruction of the shape and motion of the mouth area are often severe, since they do not match well with the speech audio. To overcome the aforementioned limitations, we present the first method for visual speech-aware perceptual reconstruction of 3D mouth expressions. We do this by proposing a "lipread" loss, which guides the fitting process so that the elicited perception from the 3D reconstructed talking head resembles that of the original video footage. We demonstrate that, interestingly, the lipread loss is better suited for 3D reconstruction of mouth movements compared to traditional landmark losses, and even direct 3D supervision. Furthermore, the devised method does not rely on any text transcriptions or corresponding audio, rendering it ideal for training in unlabeled datasets. We verify the efficiency of our method through exhaustive objective evaluations on three large-scale datasets, as well as subjective evaluation with two web-based user studies.
Pre-trained models, e.g., from ImageNet, have proven to be effective in boosting the performance of many downstream applications. It is too demanding to acquire large-scale annotations to build such models for medical imaging. Meanwhile, there are numerous clinical data (in the form of images and text reports) stored in the hospital information systems. The paired image-text data from the same patient study could be utilized for the pre-training task in a weakly supervised manner. However, the integrity, accessibility, and amount of such raw data vary across different institutes, e.g., paired vs. unpaired (image-only or text-only). In this work, we introduce an image-text pre-training framework that can learn from these raw data with mixed data inputs, i.e., paired image-text data, a mixture of paired and unpaired data. The unpaired data can be sourced from one or multiple institutes (e.g., images from one institute coupled with texts from another). Specifically, we propose a transformer-based training framework for jointly learning the representation of both the image and text data. In addition to the existing masked language modeling, multi-scale masked vision modeling is introduced as a self-supervised training task for image patch regeneration. We not only demonstrate the feasibility of pre-training across mixed data inputs but also illustrate the benefits of adopting such pre-trained models in 3 chest X-ray applications, i.e., classification, retrieval, and image regeneration. Superior results are reported in comparison to prior art using MIMIC-CXR, NIH14-CXR, and OpenI-CXR datasets.
In this paper, we focus on the challenge of learning controllable text simplifications in unsupervised settings. While this problem has been previously discussed for supervised learning algorithms, the literature on the analogies in unsupervised methods is scarse. We propose two unsupervised mechanisms for controlling the output complexity of the generated texts, namely, back translation with control tokens (a learning-based approach) and simplicity-aware beam search (decoding-based approach). We show that by nudging a back-translation algorithm to understand the relative simplicity of a text in comparison to its noisy translation, the algorithm self-supervises itself to produce the output of the desired complexity. This approach achieves competitive performance on well-established benchmarks: SARI score of 46.88% and FKGL of 3.65% on the Newsela dataset.