The detection of offensive, hateful content on social media is a challenging problem that affects many online users on a daily basis. Hateful content is often used to target a group of people based on ethnicity, gender, religion and other factors. The hate or contempt toward women has been increasing on social platforms. Misogynous content detection is especially challenging when textual and visual modalities are combined to form a single context, e.g., an overlay text embedded on top of an image, also known as meme. In this paper, we present a multimodal architecture that combines textual and visual features in order to detect misogynous meme content. The proposed architecture is evaluated in the SemEval-2022 Task 5: MAMI - Multimedia Automatic Misogyny Identification challenge under the team name TIB-VA. Our solution obtained the best result in the Task-B where the challenge is to classify whether a given document is misogynous and further identify the main sub-classes of shaming, stereotype, objectification, and violence.
This paper presents a new approach for end-to-end audio-visual multi-talker speech recognition. The approach, referred to here as the visual context attention model (VCAM), is important because it uses the available video information to assign decoded text to one of multiple visible faces. This essentially resolves the label ambiguity issue associated with most multi-talker modeling approaches which can decode multiple label strings but cannot assign the label strings to the correct speakers. This is implemented as a transformer-transducer based end-to-end model and evaluated using a two speaker audio-visual overlapping speech dataset created from YouTube videos. It is shown in the paper that the VCAM model improves performance with respect to previously reported audio-only and audio-visual multi-talker ASR systems.
Humans use natural language to compose common concepts from their environment into plausible, day-to-day scene descriptions. However, such generative commonsense reasoning (GCSR) skills are lacking in state-of-the-art text generation methods. Descriptive sentences about arbitrary concepts generated by neural text generation models (e.g., pre-trained text-to-text Transformers) are often grammatically fluent but may not correspond to human common sense, largely due to their lack of mechanisms to capture concept relations, to identify implicit concepts, and to perform generalizable reasoning about unseen concept compositions. In this paper, we propose an Imagine-and-Verbalize (I&V) method, which learns to imagine a relational scene knowledge graph (SKG) with relations between the input concepts, and leverage the SKG as a constraint when generating a plausible scene description. We collect and harmonize a set of knowledge resources from different domains and modalities, providing a rich auxiliary supervision signal for I&V. The experiments demonstrate the effectiveness of I&V in improving language models on both concept-to-sentence and concept-to-story generation tasks, while enabling the model to learn well from fewer task examples and generate SKGs that make common sense to human annotators.
Ideal point models analyze lawmakers' votes to quantify their political positions, or ideal points. But votes are not the only way to express a political position. Lawmakers also give speeches, release press statements, and post tweets. In this paper, we introduce the text-based ideal point model (TBIP), an unsupervised probabilistic topic model that analyzes texts to quantify the political positions of its authors. We demonstrate the TBIP with two types of politicized text data: U.S. Senate speeches and senator tweets. Though the model does not analyze their votes or political affiliations, the TBIP separates lawmakers by party, learns interpretable politicized topics, and infers ideal points close to the classical vote-based ideal points. One benefit of analyzing texts, as opposed to votes, is that the TBIP can estimate ideal points of anyone who authors political texts, including non-voting actors. To this end, we use it to study tweets from the 2020 Democratic presidential candidates. Using only the texts of their tweets, it identifies them along an interpretable progressive-to-moderate spectrum.
We propose a novel framework to understand the text by converting sentences or articles into video-like 3-dimensional tensors. Each frame, corresponding to a slice of the tensor, is a word image that is rendered by the word's shape. The length of the tensor equals to the number of words in the sentence or article. The proposed transformation from the text to a 3-dimensional tensor makes it very convenient to implement an $n$-gram model with convolutional neural networks for text analysis. Concretely, we impose a 3-dimensional convolutional kernel on the 3-dimensional text tensor. The first two dimensions of the convolutional kernel size equal the size of the word image and the last dimension of the kernel size is $n$. That is, every time when we slide the 3-dimensional kernel over a word sequence, the convolution covers $n$ word images and outputs a scalar. By iterating this process continuously for each $n$-gram along with the sentence or article with multiple kernels, we obtain a 2-dimensional feature map. A subsequent 1-dimensional max-over-time pooling is applied to this feature map, and three fully-connected layers are used for conducting text classification finally. Experiments of several text classification datasets demonstrate surprisingly superior performances using the proposed model in comparison with existing methods.
The medical conversational system can relieve the burden of doctors and improve the efficiency of healthcare, especially during the pandemic. This paper presents a medical conversational question answering (CQA) system based on the multi-modal knowledge graph, namely "LingYi", which is designed as a pipeline framework to maintain high flexibility. Our system utilizes automated medical procedures including medical triage, consultation, image-text drug recommendation and record. To conduct knowledge-grounded dialogues with patients, we first construct a Chinese Medical Multi-Modal Knowledge Graph (CM3KG) and collect a large-scale Chinese Medical CQA (CMCQA) dataset. Compared with the other existing medical question-answering systems, our system adopts several state-of-the-art technologies including medical entity disambiguation and medical dialogue generation, which is more friendly to provide medical services to patients. In addition, we have open-sourced our codes which contain back-end models and front-end web pages at https://github.com/WENGSYX/LingYi. The datasets including CM3KG at https://github.com/WENGSYX/CM3KG and CMCQA at https://github.com/WENGSYX/CMCQA are also released to further promote future research.
We describe a sequence-to-sequence neural network which can directly generate speech waveforms from text inputs. The architecture extends the Tacotron model by incorporating a normalizing flow into the autoregressive decoder loop. Output waveforms are modeled as a sequence of non-overlapping fixed-length frames, each one containing hundreds of samples. The interdependencies of waveform samples within each frame are modeled using the normalizing flow, enabling parallel training and synthesis. Longer-term dependencies are handled autoregressively by conditioning each flow on preceding frames. This model can be optimized directly with maximum likelihood, without using intermediate, hand-designed features nor additional loss terms. Contemporary state-of-the-art text-to-speech (TTS) systems use a cascade of separately learned models: one (such as Tacotron) which generates intermediate features (such as spectrograms) from text, followed by a vocoder (such as WaveRNN) which generates waveform samples from the intermediate features. The proposed system, in contrast, does not use a fixed intermediate representation, and learns all parameters end-to-end. Experiments show that the proposed model generates speech with quality approaching a state-of-the-art neural TTS system, with significantly improved generation speed.
Objective: Causality mining is an active research area, which requires the application of state-of-the-art natural language processing techniques. In the healthcare domain, medical experts create clinical text to overcome the limitation of well-defined and schema driven information systems. The objective of this research work is to create a framework, which can convert clinical text into causal knowledge. Methods: A practical approach based on term expansion, phrase generation, BERT based phrase embedding and semantic matching, semantic enrichment, expert verification, and model evolution has been used to construct a comprehensive causality mining framework. This active transfer learning based framework along with its supplementary services, is able to extract and enrich, causal relationships and their corresponding entities from clinical text. Results: The multi-model transfer learning technique when applied over multiple iterations, gains performance improvements in terms of its accuracy and recall while keeping the precision constant. We also present a comparative analysis of the presented techniques with their common alternatives, which demonstrate the correctness of our approach and its ability to capture most causal relationships. Conclusion: The presented framework has provided cutting-edge results in the healthcare domain. However, the framework can be tweaked to provide causality detection in other domains, as well. Significance: The presented framework is generic enough to be utilized in any domain, healthcare services can gain massive benefits due to the voluminous and various nature of its data. This causal knowledge extraction framework can be used to summarize clinical text, create personas, discover medical knowledge, and provide evidence to clinical decision making.
Stance detection is commonly defined as the automatic process of determining the positions of text producers, towards a target. In this paper, we define a research problem closely related to stance detection, namely, stance quantification, for the first time. We define stance quantification on a pair including (1) a set of natural language text items and (2) a target. At the end of the stance quantification process, a triple is obtained which consists of the percentages of the number of text items classified as Favor, Against, Neither, respectively, towards the target in the input pair. Also defined in the current paper is a significant subproblem of the stance quantification problem, namely, multi-target stance quantification. We believe that stance quantification at the aggregate level can lead to fruitful results in many application settings, and furthermore, stance quantification might be the sole stance related analysis alternative in settings where privacy concerns prevent researchers from applying generic stance detection.
To make full use of computer vision technology in stores, it is required to consider the actual needs that fit the characteristics of the retail scene. Pursuing this goal, we introduce the United Retail Datasets (Unitail), a large-scale benchmark of basic visual tasks on products that challenges algorithms for detecting, reading, and matching. With 1.8M quadrilateral-shaped instances annotated, the Unitail offers a detection dataset to align product appearance better. Furthermore, it provides a gallery-style OCR dataset containing 1454 product categories, 30k text regions, and 21k transcriptions to enable robust reading on products and motivate enhanced product matching. Besides benchmarking the datasets using various state-of-the-arts, we customize a new detector for product detection and provide a simple OCR-based matching solution that verifies its effectiveness.