PaddleSpeech is an open-source all-in-one speech toolkit. It aims at facilitating the development and research of speech processing technologies by providing an easy-to-use command-line interface and a simple code structure. This paper describes the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to-speech tasks. PaddleSpeech achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods. It also provides recipes and pretrained models to quickly reproduce the experimental results in this paper. PaddleSpeech is publicly avaiable at https://github.com/PaddlePaddle/PaddleSpeech.
Automatically summarizing patients' main problems from daily progress notes using natural language processing methods helps to battle against information and cognitive overload in hospital settings and potentially assists providers with computerized diagnostic decision support. Problem list summarization requires a model to understand, abstract, and generate clinical documentation. In this work, we propose a new NLP task that aims to generate a list of problems in a patient's daily care plan using input from the provider's progress notes during hospitalization. We investigate the performance of T5 and BART, two state-of-the-art seq2seq transformer architectures, in solving this problem. We provide a corpus built on top of progress notes from publicly available electronic health record progress notes in the Medical Information Mart for Intensive Care (MIMIC)-III. T5 and BART are trained on general domain text, and we experiment with a data augmentation method and a domain adaptation pre-training method to increase exposure to medical vocabulary and knowledge. Evaluation methods include ROUGE, BERTScore, cosine similarity on sentence embedding, and F-score on medical concepts. Results show that T5 with domain adaptive pre-training achieves significant performance gains compared to a rule-based system and general domain pre-trained language models, indicating a promising direction for tackling the problem summarization task.
People have recently begun communicating their thoughts and viewpoints through user-generated multimedia material on social networking websites. This information can be images, text, videos, or audio. Recent years have seen a rise in the frequency of occurrence of this pattern. Twitter is one of the most extensively utilized social media sites, and it is also one of the finest locations to get a sense of how people feel about events that are linked to the Monkeypox sickness. This is because tweets on Twitter are shortened and often updated, both of which contribute to the platform's character. The fundamental objective of this study is to get a deeper comprehension of the diverse range of reactions people have in response to the presence of this condition. This study focuses on finding out what individuals think about monkeypox illnesses, which presents a hybrid technique based on CNN and LSTM. We have considered all three possible polarities of a user's tweet: positive, negative, and neutral. An architecture built on CNN and LSTM is utilized to determine how accurate the prediction models are. The recommended model's accuracy was 94% on the monkeypox tweet dataset. Other performance metrics such as accuracy, recall, and F1-score were utilized to test our models and results in the most time and resource-effective manner. The findings are then compared to more traditional approaches to machine learning. The findings of this research contribute to an increased awareness of the monkeypox infection in the general population.
The spread of digital disinformation (aka "fake news") is arguably one of the most significant threats on the Internet which can cause individual and societal harm of large scales. The susceptibility to fake news attacks hinges on whether Internet users perceive a fake news article/snippet to be legitimate after reading it. In this paper, we attempt to garner an in-depth understanding of users' susceptibility to text-centric fake news attacks via a neuro-cognitive methodology. We investigate the neural underpinnings relevant to fake/real news through EEG. We run an experiment with human users to pursue a thorough investigation of users' perception and cognitive processing of fake/real news. We analyze the neural activity associated with the fake/real news detection task for different categories of news articles. Our results show there may be no statistically significant or automatically inferable differences in the way the human brain processes the fake vs. real news, while marked differences are observed when people are subject to (real/fake) news vs. resting state and even between some different categories of fake news. This neuro-cognitive finding may help to justify users' susceptibility to fake news attacks, as also confirmed from the behavioral analysis. In other words, the fake news articles may seem almost indistinguishable from the real news articles in both behavioral and neural domains. Our work serves to dissect the fundamental neural phenomena underlying fake news attacks and explains users' susceptibility to these attacks through the limits of human biology. We believe this could be a notable insight for the researchers and practitioners suggesting the human detection of fake news might be ineffective, which may also have an adverse impact on the design of automated detection approaches that crucially rely upon human labeling of text articles for building training models
In this work, we present a Web-based annotation tool `Relation Triplets Extractor' \footnote{https://abera87.github.io/annotate/} (RTE) for annotating relation triplets from the text. Relation extraction is an important task for extracting structured information about real-world entities from the unstructured text available on the Web. In relation extraction, we focus on binary relation that refers to relations between two entities. Recently, many supervised models are proposed to solve this task, but they mostly use noisy training data obtained using the distant supervision method. In many cases, evaluation of the models is also done based on a noisy test dataset. The lack of annotated clean dataset is a key challenge in this area of research. In this work, we built a web-based tool where researchers can annotate datasets for relation extraction on their own very easily. We use a server-less architecture for this tool, and the entire annotation operation is processed using client-side code. Thus it does not suffer from any network latency, and the privacy of the user's data is also maintained. We hope that this tool will be beneficial for the researchers to advance the field of relation extraction.
In the field of text-independent speaker recognition, dynamic models that change along the time axis have been proposed to consider the phoneme-varying characteristics of speech. However, detailed analysis on how dynamic models work depending on phonemes is insufficient. In this paper, we propose temporal dynamic CNN (TDY-CNN) that considers temporal variation of phonemes by applying kernels optimally adapt to each time bin. These kernels adapt to time bins by applying weighted sum of trained basis kernels. Then, an analysis on how adaptive kernels work on different phonemes in various layers is carried out. TDY-ResNet-38(x0.5) using six basis kernels shows better speaker verification performance than baseline model ResNet-38(x0.5) does, with an equal error rate (EER) of 1.48%. In addition, we showed that adaptive kernels depend on phoneme groups and more phoneme-specific at early layer. Temporal dynamic model adapts itself to phonemes without explicitly given phoneme information during training, and the results show that the necessity to consider phoneme variation within utterances for more accurate and robust text-independent speaker verification.
A crucial component for the scene text based reasoning required for TextVQA and TextCaps datasets involve detecting and recognizing text present in the images using an optical character recognition (OCR) system. The current systems are crippled by the unavailability of ground truth text annotations for these datasets as well as lack of scene text detection and recognition datasets on real images disallowing the progress in the field of OCR and evaluation of scene text based reasoning in isolation from OCR systems. In this work, we propose TextOCR, an arbitrary-shaped scene text detection and recognition with 900k annotated words collected on real images from TextVQA dataset. We show that current state-of-the-art text-recognition (OCR) models fail to perform well on TextOCR and that training on TextOCR helps achieve state-of-the-art performance on multiple other OCR datasets as well. We use a TextOCR trained OCR model to create PixelM4C model which can do scene text based reasoning on an image in an end-to-end fashion, allowing us to revisit several design choices to achieve new state-of-the-art performance on TextVQA dataset.
With Internet users constantly leaving a trail of text, whether through blogs, emails, or social media posts, the ability to write and protest anonymously is being eroded because artificial intelligence, when given a sample of previous work, can match text with its author out of hundreds of possible candidates. Existing approaches to authorship anonymization, also known as authorship obfuscation, often focus on protecting binary demographic attributes rather than identity as a whole. Even those that do focus on obfuscating identity require manual feedback, lose the coherence of the original sentence, or only perform well given a limited subset of authors. In this paper, we develop a new approach to authorship anonymization by constructing a generative adversarial network that protects identity and optimizes for three different losses corresponding to anonymity, fluency, and content preservation. Our fully automatic method achieves comparable results to other methods in terms of content preservation and fluency, but greatly outperforms baselines in regards to anonymization. Moreover, our approach is able to generalize well to an open-set context and anonymize sentences from authors it has not encountered before.
Documents often contain complex physical structures, which make the Document Layout Analysis (DLA) task challenging. As a pre-processing step for content extraction, DLA has the potential to capture rich information in historical or scientific documents on a large scale. Although many deep-learning-based methods from computer vision have already achieved excellent performance in detecting \emph{Figure} from documents, they are still unsatisfactory in recognizing the \emph{List}, \emph{Table}, \emph{Text} and \emph{Title} category blocks in DLA. This paper proposes a VTLayout model fusing the documents' deep visual, shallow visual, and text features to localize and identify different category blocks. The model mainly includes two stages, and the three feature extractors are built in the second stage. In the first stage, the Cascade Mask R-CNN model is applied directly to localize all category blocks of the documents. In the second stage, the deep visual, shallow visual, and text features are extracted for fusion to identify the category blocks of documents. As a result, we strengthen the classification power of different category blocks based on the existing localization technique. The experimental results show that the identification capability of the VTLayout is superior to the most advanced method of DLA based on the PubLayNet dataset, and the F1 score is as high as 0.9599.
The task of organizing a shuffled set of sentences into a coherent text is important in NLP and has been used to evaluate a machine's understanding of causal and temporal relations. We present Reorder-BART (RE-BART), a sentence ordering framework which leverages a pre-trained transformer-based model to identify a coherent order for a given set of shuffled sentences. We reformulate the task as a conditional text-to-marker generation setup where the input is a set of shuffled sentences with sentence-specific markers and output is a sequence of position markers of the ordered text. Our framework achieves the state-of-the-art performance across six datasets in Perfect Match Ratio (PMR) and Kendall's tau ($\tau$) metric. We perform evaluations in a zero-shot setting, showcasing that our model is able to generalize well across other datasets. We additionally perform a series of experiments to understand the functioning and explore the limitations of our framework.