An intuitive way to search for images is to use queries composed of an example image and a complementary text. While the first provides rich and implicit context for the search, the latter explicitly calls for new traits, or specifies how some elements of the example image should be changed to retrieve the desired target image. Current approaches typically combine the features of each of the two elements of the query into a single representation, which can then be compared to the ones of the potential target images. Our work aims at shedding new light on the task by looking at it through the prism of two familiar and related frameworks: text-to-image and image-to-image retrieval. Taking inspiration from them, we exploit the specific relation of each query element with the targeted image and derive light-weight attention mechanisms which enable to mediate between the two complementary modalities. We validate our approach on several retrieval benchmarks, querying with images and their associated free-form text modifiers. Our method obtains state-of-the-art results without resorting to side information, multi-level features, heavy pre-training nor large architectures as in previous works.
Conditioned diffusion models have demonstrated state-of-the-art text-to-image synthesis capacity. Recently, most works focus on synthesizing independent images; While for real-world applications, it is common and necessary to generate a series of coherent images for story-stelling. In this work, we mainly focus on story visualization and continuation tasks and propose AR-LDM, a latent diffusion model auto-regressively conditioned on history captions and generated images. Moreover, AR-LDM can generalize to new characters through adaptation. To our best knowledge, this is the first work successfully leveraging diffusion models for coherent visual story synthesizing. Quantitative results show that AR-LDM achieves SoTA FID scores on PororoSV, FlintstonesSV, and the newly introduced challenging dataset VIST containing natural images. Large-scale human evaluations show that AR-LDM has superior performance in terms of quality, relevance, and consistency.
While the NLP community is generally aware of resource disparities among languages, we lack research that quantifies the extent and types of such disparity. Prior surveys estimating the availability of resources based on the number of datasets can be misleading as dataset quality varies: many datasets are automatically induced or translated from English data. To provide a more comprehensive picture of language resources, we examine the characteristics of 156 publicly available NLP datasets. We manually annotate how they are created, including input text and label sources and tools used to build them, and what they study, tasks they address and motivations for their creation. After quantifying the qualitative NLP resource gap across languages, we discuss how to improve data collection in low-resource languages. We survey language-proficient NLP researchers and crowd workers per language, finding that their estimated availability correlates with dataset availability. Through crowdsourcing experiments, we identify strategies for collecting high-quality multilingual data on the Mechanical Turk platform. We conclude by making macro and micro-level suggestions to the NLP community and individual researchers for future multilingual data development.
Online learning platforms provide learning materials and answers to students' academic questions by experts, peers, or systems. This paper explores question-type identification as a step in content understanding for an online learning platform. The aim of the question-type identifier is to categorize question types based on their structure and complexity, using the question text, subject, and structural features. We have defined twelve question-type classes, including Multiple-Choice Question (MCQ), essay, and others. We have compiled an internal dataset of students' questions and used a combination of weak-supervision techniques and manual annotation. We then trained a BERT-based ensemble model on this dataset and evaluated this model on a separate human-labeled test set. Our experiments yielded an F1-score of 0.94 for MCQ binary classification and promising results for 12-class multilabel classification. We deployed the model in our online learning platform as a crucial enabler for content understanding to enhance the student learning experience.
Far beyond learning long-range interactions of natural language, transformers are becoming the de-facto standard for many vision tasks with their power and scalabilty. Especially with cross-modal tasks between image and text, vector quantized variational autoencoders (VQ-VAEs) are widely used to make a raw RGB image into a sequence of feature vectors. To better leverage the correlation between image and text, we propose L-Verse, a novel architecture consisting of feature-augmented variational autoencoder (AugVAE) and bidirectional auto-regressive transformer (BiART) for text-to-image and image-to-text generation. Our AugVAE shows the state-of-the-art reconstruction performance on ImageNet1K validation set, along with the robustness to unseen images in the wild. Unlike other models, BiART can distinguish between image (or text) as a conditional reference and a generation target. L-Verse can be directly used for image-to-text or text-to-image generation tasks without any finetuning or extra object detection frameworks. In quantitative and qualitative experiments, L-Verse shows impressive results against previous methods in both image-to-text and text-to-image generation on MS-COCO Captions. We furthermore assess the scalability of L-Verse architecture on Conceptual Captions and present the initial results of bidirectional vision-language representation learning on general domain. Codes available at: https://github.com/tgisaturday/L-Verse
Due to the ambiguity of homophones, Chinese Spell Checking (CSC) has widespread applications. Existing systems typically utilize BERT for text encoding. However, CSC requires the model to account for both phonetic and graphemic information. To adapt BERT to the CSC task, we propose a token-level self-distillation contrastive learning method. We employ BERT to encode both the corrupted and corresponding correct sentence. Then, we use contrastive learning loss to regularize corrupted tokens' hidden states to be closer to counterparts in the correct sentence. On three CSC datasets, we confirmed our method provides a significant improvement above baselines.
Compared to sequential learning models, graph-based neural networks exhibit excellent ability in capturing global information and have been used for semi-supervised learning tasks. Most Graph Convolutional Networks are designed with the single-dimensional edge feature and failed to utilise the rich edge information about graphs. This paper introduces the ME-GCN (Multi-dimensional Edge-enhanced Graph Convolutional Networks) for semi-supervised text classification. A text graph for an entire corpus is firstly constructed to describe the undirected and multi-dimensional relationship of word-to-word, document-document, and word-to-document. The graph is initialised with corpus-trained multi-dimensional word and document node representation, and the relations are represented according to the distance of those words/documents nodes. Then, the generated graph is trained with ME-GCN, which considers the edge features as multi-stream signals, and each stream performs a separate graph convolutional operation. Our ME-GCN can integrate a rich source of graph edge information of the entire text corpus. The results have demonstrated that our proposed model has significantly outperformed the state-of-the-art methods across eight benchmark datasets.
Transformer models have achieved great success across many NLP problems. However, previous studies in automated ICD coding concluded that these models fail to outperform some of the earlier solutions such as CNN-based models. In this paper we challenge this conclusion. We present a simple and scalable method to process long text with the existing transformer models such as BERT. We show that this method significantly improves the previous results reported for transformer models in ICD coding, and is able to outperform one of the prominent CNN-based methods.
The flourishing blossom of deep learning has witnessed the rapid development of text recognition in recent years. However, the existing text recognition methods are mainly for English texts, whereas ignoring the pivotal role of Chinese texts. As another widely-spoken language, Chinese text recognition in all ways has extensive application markets. Based on our observations, we attribute the scarce attention on Chinese text recognition to the lack of reasonable dataset construction standards, unified evaluation methods, and results of the existing baselines. To fill this gap, we manually collect Chinese text datasets from publicly available competitions, projects, and papers, then divide them into four categories including scene, web, document, and handwriting datasets. Furthermore, we evaluate a series of representative text recognition methods on these datasets with unified evaluation methods to provide experimental results. By analyzing the experimental results, we surprisingly observe that state-of-the-art baselines for recognizing English texts cannot perform well on Chinese scenarios. We consider that there still remain numerous challenges under exploration due to the characteristics of Chinese texts, which are quite different from English texts. The code and datasets are made publicly available at https://github.com/FudanVI/benchmarking-chinese-text-recognition.
As an important task in multimodal context understanding, Text-VQA (Visual Question Answering) aims at question answering through reading text information in images. It differentiates from the original VQA task as Text-VQA requires large amounts of scene-text relationship understanding, in addition to the cross-modal grounding capability. In this paper, we propose Localize, Group, and Select (LOGOS), a novel model which attempts to tackle this problem from multiple aspects. LOGOS leverages two grounding tasks to better localize the key information of the image, utilizes scene text clustering to group individual OCR tokens, and learns to select the best answer from different sources of OCR (Optical Character Recognition) texts. Experiments show that LOGOS outperforms previous state-of-the-art methods on two Text-VQA benchmarks without using additional OCR annotation data. Ablation studies and analysis demonstrate the capability of LOGOS to bridge different modalities and better understand scene text.