In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data. First, we leverage global action information to catalyze the mutual interactions between linguistic texts and local regional objects. It uncovers global and local visual clues from paired video sequences and text descriptions for detailed visual and text relation modeling. Second, we introduce an ENtangled Transformer block (ENT) to encode three sources of information, i.e., global actions, local regional objects, and linguistic descriptions. Global-local correspondences are discovered via judicious clues extraction from contextual information. It enforces the joint videotext representation to be aware of fine-grained objects as well as global human intention. We validate the generalization capability of ActBERT on downstream video-and language tasks, i.e., text-video clip retrieval, video captioning, video question answering, action segmentation, and action step localization. ActBERT significantly outperforms the state-of-the-arts, demonstrating its superiority in video-text representation learning.
Text localization from the digital image is the first step for the optical character recognition task. Conventional image processing based text localization performs adequately for specific examples. Yet, a general text localization are only archived by recent deep-learning based modalities. Here we present document Text Localization Generative Adversarial Nets (TLGAN) which are deep neural networks to perform the text localization from digital image. TLGAN is an versatile and easy-train text localization model requiring a small amount of data. Training only ten labeled receipt images from Robust Reading Challenge on Scanned Receipts OCR and Information Extraction (SROIE), TLGAN achieved 99.83% precision and 99.64% recall for SROIE test data. Our TLGAN is a practical text localization solution requiring minimal effort for data labeling and model training and producing a state-of-art performance.
User sessions empower many search and recommendation tasks on a daily basis. Such session data are semi-structured, which encode heterogeneous relations between queries and products, and each item is described by the unstructured text. Despite recent advances in self-supervised learning for text or graphs, there lack of self-supervised learning models that can effectively capture both intra-item semantics and inter-item interactions for semi-structured sessions. To fill this gap, we propose CERES, a graph-based transformer model for semi-structured session data. CERES learns representations that capture both inter- and intra-item semantics with (1) a graph-conditioned masked language pretraining task that jointly learns from item text and item-item relations; and (2) a graph-conditioned transformer architecture that propagates inter-item contexts to item-level representations. We pretrained CERES using ~468 million Amazon sessions and find that CERES outperforms strong pretraining baselines by up to 9% in three session search and entity linking tasks.
While neural networks demonstrate a remarkable ability to model linguistic content, capturing contextual information related to a speaker's conversational role is an open area of research. In this work, we analyze the effect of speaker role on language use through the game of Mafia, in which participants are assigned either an honest or a deceptive role. In addition to building a framework to collect a dataset of Mafia game records, we demonstrate that there are differences in the language produced by players with different roles. We confirm that classification models are able to rank deceptive players as more suspicious than honest ones based only on their use of language. Furthermore, we show that training models on two auxiliary tasks outperforms a standard BERT-based text classification approach. We also present methods for using our trained models to identify features that distinguish between player roles, which could be used to assist players during the Mafia game.
Text simplification is concerned with reducing the language complexity and improving the readability of professional content so that the text is accessible to readers at different ages and educational levels. As a promising practice to improve the fairness and transparency of text information systems, the notion of text simplification has been mixed in existing literature, ranging all the way through assessing the complexity of single words to automatically generating simplified documents. We show that the general problem of text simplification can be formally decomposed into a compact pipeline of tasks to ensure the transparency and explanability of the process. In this paper, we present a systematic analysis of the first two steps in this pipeline: 1) predicting the complexity of a given piece of text, and 2) identifying complex components from the text considered to be complex. We show that these two tasks can be solved separately, using either lexical approaches or the state-of-the-art deep learning methods, or they can be solved jointly through an end-to-end, explainable machine learning predictor. We propose formal evaluation metrics for both tasks, through which we are able to compare the performance of the candidate approaches using multiple datasets from a diversity of domains.
Key Information Extraction (KIE) is aimed at extracting structured information (e.g. key-value pairs) from form-style documents (e.g. invoices), which makes an important step towards intelligent document understanding. Previous approaches generally tackle KIE by sequence tagging, which faces difficulty to process non-flatten sequences, especially for table-text mixed documents. These approaches also suffer from the trouble of pre-defining a fixed set of labels for each type of documents, as well as the label imbalance issue. In this work, we assume Optical Character Recognition (OCR) has been applied to input documents, and reformulate the KIE task as a region prediction problem in the two-dimensional (2D) space given a target field. Following this new setup, we develop a new KIE model named Region-based Document Understanding (RDU) that takes as input the text content and corresponding coordinates of a document, and tries to predict the result by localizing a bounding-box-like region. Our RDU first applies a layout-aware BERT equipped with a soft layout attention masking and bias mechanism to incorporate layout information into the representations. Then, a list of candidate regions is generated from the representations via a Region Proposal Module inspired by computer vision models widely applied for object detection. Finally, a Region Categorization Module and a Region Selection Module are adopted to judge whether a proposed region is valid and select the one with the largest probability from all proposed regions respectively. Experiments on four types of form-style documents show that our proposed method can achieve impressive results. In addition, our RDU model can be trained with different document types seamlessly, which is especially helpful over low-resource documents.
Cervical glandular cell (GC) detection is a key step in computer-aided diagnosis for cervical adenocarcinomas screening. It is challenging to accurately recognize GCs in cervical smears in which squamous cells are the major. Widely existing Out-Of-Distribution (OOD) data in the entire smear leads decreasing reliability of machine learning system for GC detection. Although, the State-Of-The-Art (SOTA) deep learning model can outperform pathologists in preselected regions of interest, the mass False Positive (FP) prediction with high probability is still unsolved when facing such gigapixel whole slide image. This paper proposed a novel PolarNet based on the morphological prior knowledge of GC trying to solve the FP problem via a self-attention mechanism in eight-neighbor. It estimates the polar orientation of nucleus of GC. As a plugin module, PolarNet can guide the deep feature and predicted confidence of general object detection models. In experiments, we discovered that general models based on four different frameworks can reject FP in small image set and increase the mean of average precision (mAP) by $\text{0.007}\sim\text{0.015}$ in average, where the highest exceeds the recent cervical cell detection model 0.037. By plugging PolarNet, the deployed C++ program improved by 8.8\% on accuracy of top-20 GC detection from external WSIs, while sacrificing 14.4 s of computational time. Code is available in https://github.com/Chrisa142857/PolarNet-GCdet
CodexDB is an SQL processing engine whose internals can be customized via natural language instructions. CodexDB is based on OpenAI's GPT-3 Codex model which translates text into code. It is a framework on top of GPT-3 Codex that decomposes complex SQL queries into a series of simple processing steps, described in natural language. Processing steps are enriched with user-provided instructions and descriptions of database properties. Codex translates the resulting text into query processing code. An early prototype of CodexDB is able to generate correct code for a majority of queries of the WikiSQL benchmark and can be customized in various ways.
This paper presents the results of research on supervised extractive text summarisation for scientific articles. We show that a simple sequential tagging model based only on the text within a document achieves high results against a simple classification model. Improvements can be achieved through additional sentence-level features, though these were minimal. Through further analysis, we show the potential of the sequential model relying on the structure of the document depending on the academic discipline which the document is from.
Toxic language detection systems often falsely flag text that contains minority group mentions as toxic, as those groups are often the targets of online hate. Such over-reliance on spurious correlations also causes systems to struggle with detecting implicitly toxic language. To help mitigate these issues, we create ToxiGen, a new large-scale and machine-generated dataset of 274k toxic and benign statements about 13 minority groups. We develop a demonstration-based prompting framework and an adversarial classifier-in-the-loop decoding method to generate subtly toxic and benign text with a massive pretrained language model. Controlling machine generation in this way allows ToxiGen to cover implicitly toxic text at a larger scale, and about more demographic groups, than previous resources of human-written text. We conduct a human evaluation on a challenging subset of ToxiGen and find that annotators struggle to distinguish machine-generated text from human-written language. We also find that 94.5% of toxic examples are labeled as hate speech by human annotators. Using three publicly-available datasets, we show that finetuning a toxicity classifier on our data improves its performance on human-written data substantially. We also demonstrate that ToxiGen can be used to fight machine-generated toxicity as finetuning improves the classifier significantly on our evaluation subset.