This paper presents the design and implementation of WhisperWand, a comprehensive voice and motion tracking interface for voice assistants. Distinct from prior works, WhisperWand is a precise tracking interface that can co-exist with the voice interface on low sampling rate voice assistants. Taking handwriting as a specific application, it can also capture natural strokes and the individualized style of writing while occupying only a single frequency. The core technique includes an accurate acoustic ranging method called Cross Frequency Continuous Wave (CFCW) sonar, enabling voice assistants to use ultrasound as a ranging signal while using the regular microphone system of voice assistants as a receiver. We also design a new optimization algorithm that only requires a single frequency for time difference of arrival. WhisperWand prototype achieves 73 um of median error for 1D ranging and 1.4 mm of median error in 3D tracking of an acoustic beacon using the microphone array used in voice assistants. Our implementation of an in-air handwriting interface achieves 94.1% accuracy with automatic handwriting-to-text software, similar to writing on paper (96.6%). At the same time, the error rate of voice-based user authentication only increases from 6.26% to 8.28%.
Extracting Handwritten text is one of the most important components of digitizing information and making it available for large scale setting. Handwriting Optical Character Reader (OCR) is a research problem in computer vision and natural language processing computing, and a lot of work has been done for English, but unfortunately, very little work has been done for low resourced languages such as Urdu. Urdu language script is very difficult because of its cursive nature and change of shape of characters based on it's relative position, therefore, a need arises to propose a model which can understand complex features and generalize it for every kind of handwriting style. In this work, we propose a transformer based Urdu Handwritten text extraction model. As transformers have been very successful in Natural Language Understanding task, we explore them further to understand complex Urdu Handwriting.
We study node representation learning on heterogeneous text-rich networks, where nodes and edges are multi-typed and some types of nodes are associated with text information. Although recent studies on graph neural networks (GNNs) and pretrained language models (PLMs) have demonstrated their power in encoding network and text signals, respectively, less focus has been given to delicately coupling these two types of models on heterogeneous text-rich networks. Specifically, existing GNNs rarely model text in each node in a contextualized way; existing PLMs can hardly be applied to characterize graph structures due to their sequence architecture. In this paper, we propose Heterformer, a Heterogeneous GNN-nested transformer that blends GNNs and PLMs into a unified model. Different from previous "cascaded architectures" that directly add GNN layers upon a PLM, our Heterformer alternately stacks two modules - a graph-attention-based neighbor aggregation module and a transformer-based text and neighbor joint encoding module - to facilitate thorough mutual enhancement between network and text signals. Meanwhile, Heterformer is capable of characterizing network heterogeneity and nodes without text information. Comprehensive experiments on three large-scale datasets from different domains demonstrate the superiority of Heterformer over state-of-the-art baselines in link prediction, transductive/inductive node classification, node clustering, and semantics-based retrieval.
Writing is, by nature, a strategic, adaptive, and more importantly, an iterative process. A crucial part of writing is editing and revising the text. Previous works on text revision have focused on defining edit intention taxonomies within a single domain or developing computational models with a single level of edit granularity, such as sentence-level edits, which differ from human's revision cycles. This work describes IteraTeR: the first large-scale, multi-domain, edit-intention annotated corpus of iteratively revised text. In particular, IteraTeR is collected based on a new framework to comprehensively model the iterative text revisions that generalize to various domains of formal writing, edit intentions, revision depths, and granularities. When we incorporate our annotated edit intentions, both generative and edit-based text revision models significantly improve automatic evaluations. Through our work, we better understand the text revision process, making vital connections between edit intentions and writing quality, enabling the creation of diverse corpora to support computational modeling of iterative text revisions.
With recent developments in digitization of clinical psychology, NLP research community has revolutionized the field of mental health detection on social media. Existing research in mental health analysis revolves around the cross-sectional studies to classify users' intent on social media. For in-depth analysis, we investigate existing classifiers to solve the problem of causal categorization which suggests the inefficiency of learning based methods due to limited training samples. To handle this challenge, we use transformer models and demonstrate the efficacy of a pre-trained transfer learning on "CAMS" dataset. The experimental result improves the accuracy and depicts the importance of identifying cause-and-effect relationships in the underlying text.
This paper introduces supervised machine learning to the literature measuring corporate culture from text documents. We compile a unique data set of employee reviews that were labeled by human evaluators with respect to the information the reviews reveal about the firms' corporate culture. Using this data set, we fine-tune state-of-the-art transformer-based language models to perform the same classification task. In out-of-sample predictions, our language models classify 16 to 28 percent points more of employee reviews in line with human evaluators than traditional approaches of text classification.
We propose CLIP-Actor, a text-driven motion recommendation and neural mesh stylization system for human mesh animation. CLIP-Actor animates a 3D human mesh to conform to a text prompt by recommending a motion sequence and learning mesh style attributes. Prior work fails to generate plausible results when the artist-designed mesh content does not conform to the text from the beginning. Instead, we build a text-driven human motion recommendation system by leveraging a large-scale human motion dataset with language labels. Given a natural language prompt, CLIP-Actor first suggests a human motion that conforms to the prompt in a coarse-to-fine manner. Then, we propose a synthesize-through-optimization method that detailizes and texturizes a recommended mesh sequence in a disentangled way from the pose of each frame. It allows the style attribute to conform to the prompt in a temporally-consistent and pose-agnostic manner. The decoupled neural optimization also enables spatio-temporal view augmentation from multi-frame human motion. We further propose the mask-weighted embedding attention, which stabilizes the optimization process by rejecting distracting renders containing scarce foreground pixels. We demonstrate that CLIP-Actor produces plausible and human-recognizable style 3D human mesh in motion with detailed geometry and texture from a natural language prompt.
The state-of-the-art language model-based automatic metrics, e.g. BARTScore, benefiting from large-scale contextualized pre-training, have been successfully used in a wide range of natural language generation (NLG) tasks, including machine translation, text summarization, and data-to-text. Recent studies show that considering both major errors (e.g. mistranslated tokens) and minor errors (e.g. imperfections in fluency) can produce high-quality human judgments. This inspires us to approach the final goal of the evaluation metrics (human-like evaluations) by automatic error analysis. To this end, we augment BARTScore by incorporating the human-like error analysis strategies, namely BARTScore++, where the final score consists of both the evaluations of major errors and minor errors. Experimental results show that BARTScore++ can consistently improve the performance of vanilla BARTScore and outperform existing top-scoring metrics in 20 out of 25 test settings. We hope our technique can also be extended to other pre-trained model-based metrics. We will release our code and scripts to facilitate the community.
Graph Convolutional Networks (GCN) have been effective at tasks that have rich relational structure and can preserve global structure information of a dataset in graph embeddings. Recently, many researchers focused on examining whether GCNs could handle different Natural Language Processing tasks, especially text classification. While applying GCNs to text classification is well-studied, its graph construction techniques, such as node/edge selection and their feature representation, and the optimal GCN learning mechanism in text classification is rather neglected. In this paper, we conduct a comprehensive analysis of the role of node and edge embeddings in a graph and its GCN learning techniques in text classification. Our analysis is the first of its kind and provides useful insights into the importance of each graph node/edge construction mechanism when applied at the GCN training/testing in different text classification benchmarks, as well as under its semi-supervised environment.
We aim to diagnose the potential biases in image classifiers. To this end, prior works manually labeled biased attributes or visualized biased features, which need high annotation costs or are often ambiguous to interpret. Instead, we leverage two types (generative and discriminative) of pre-trained vision-language models to describe the visual bias as a word. Specifically, we propose bias-to-text (B2T), which generates captions of the mispredicted images using a pre-trained captioning model to extract the common keywords that may describe visual biases. Then, we categorize the bias type as spurious correlation or majority bias by checking if it is specific or agnostic to the class, based on the similarity of class-wise mispredicted images and the keyword upon a pre-trained vision-language joint embedding space, e.g., CLIP. We demonstrate that the proposed simple and intuitive scheme can recover well-known gender and background biases, and discover novel ones in real-world datasets. Moreover, we utilize B2T to compare the classifiers using different architectures or training methods. Finally, we show that one can obtain debiased classifiers using the B2T bias keywords and CLIP, in both zero-shot and full-shot manners, without using any human annotation on the bias.