Background: The performance of biometric modalities based on things done by the subject, like signature and text-based recognition, may be affected by the subject state. Fatigue is one of the conditions that can significantly affect the outcome of handwriting tasks. Recent research has already shown that physical fatigue produces measurable differences in some features extracted from common writing and drawing tasks. It is important to establish to which extent physical fatigue contributes to the intra-person variability observed in these biometric modalities and also to know whether the performance of recognition methods is affected by fatigue. Goal: In this paper we assess the impact of fatigue on intra-user variability and on the performance of signature-based and text-based writer recognition approaches encompassing both identification and verification. Methods: Several signature and text recognition methods are considered and applied to samples gathered after different levels of induced fatigue, measured by metabolic and mechanical assessment and, also by subjective perception. The recognition methods are Dynamic Time Warping and Multi Section Vector Quantization, for signatures, and Allographic Text-Dependent Recognition for text in capital letters. For each fatigue level, the identification and verification performance of these methods is measured. Results: Signature shows no statistically significant intra-user impact, but text does. On the other hand, performance of signature-based recognition approaches is negatively impacted by fatigue whereas the impact is not noticeable in text-based recognition, provided long enough sequences are considered.
Mainstream Video-Language Pre-training models \cite{actbert,clipbert,violet} consist of three parts, a video encoder, a text encoder, and a video-text fusion Transformer. They pursue better performance via utilizing heavier unimodal encoders or multimodal fusion Transformers, resulting in increased parameters with lower efficiency in downstream tasks. In this work, we for the first time introduce an end-to-end video-language model, namely \textit{all-in-one Transformer}, that embeds raw video and textual signals into joint representations using a unified backbone architecture. We argue that the unique temporal information of video data turns out to be a key barrier hindering the design of a modality-agnostic Transformer. To overcome the challenge, we introduce a novel and effective token rolling operation to encode temporal representations from video clips in a non-parametric manner. The careful design enables the representation learning of both video-text multimodal inputs and unimodal inputs using a unified backbone model. Our pre-trained all-in-one Transformer is transferred to various downstream video-text tasks after fine-tuning, including text-video retrieval, video-question answering, multiple choice and visual commonsense reasoning. State-of-the-art performances with the minimal model FLOPs on nine datasets demonstrate the superiority of our method compared to the competitive counterparts. The code and pretrained model have been released in https://github.com/showlab/all-in-one.
Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text. Conventional neural models are insufficient for logical reasoning, while symbolic reasoners cannot directly apply to text. To meet the challenge, we present a neural-symbolic approach which, to predict an answer, passes messages over a graph representing logical relations between text units. It incorporates an adaptive logic graph network (AdaLoGN) which adaptively infers logical relations to extend the graph and, essentially, realizes mutual and iterative reinforcement between neural and symbolic reasoning. We also implement a novel subgraph-to-node message passing mechanism to enhance context-option interaction for answering multiple-choice questions. Our approach shows promising results on ReClor and LogiQA.
Recent work in spoken language modeling shows the possibility of learning a language unsupervisedly from raw audio without any text labels. The approach relies first on transforming the audio into a sequence of discrete units (or pseudo-text) and then training a language model directly on such pseudo-text. Is such a discrete bottleneck necessary, potentially introducing irreversible errors in the encoding of the speech signal, or could we learn a language model without discrete units at all? In this work, show that discretization is indeed essential for good results in spoken language modeling, but that can omit the discrete bottleneck if we use using discrete target features from a higher level than the input features. We also show that an end-to-end model trained with discrete target like HuBERT achieves similar results as the best language model trained on pseudo-text on a set of zero-shot spoken language modeling metrics from the Zero Resource Speech Challenge 2021.
Some grammatical error correction (GEC) systems incorporate hand-crafted rules and achieve positive results. However, manually defining rules is time-consuming and laborious. In view of this, we propose a method to mine error templates for GEC automatically. An error template is a regular expression aiming at identifying text errors. We use the web crawler to acquire such error templates from the Internet. For each template, we further select the corresponding corrective action by using the language model perplexity as a criterion. We have accumulated 1,119 error templates for Chinese GEC based on this method. Experimental results on the newly proposed CTC-2021 Chinese GEC benchmark show that combing our error templates can effectively improve the performance of a strong GEC system, especially on two error types with very little training data. Our error templates are available at \url{https://github.com/HillZhang1999/gec_error_template}.
Gene/protein interactions provide critical information for a thorough understanding of cellular processes. Recently, considerable interest and effort has been focused on the construction and analysis of genome-wide gene networks. The large body of biomedical literature is an important source of gene/protein interaction information. Recent advances in text mining tools have made it possible to automatically extract such documented interactions from free-text literature. In this paper, we propose a comprehensive framework for constructing and analyzing large-scale gene functional networks based on the gene/protein interactions extracted from biomedical literature repositories using text mining tools. Our proposed framework consists of analyses of the network topology, network topology-gene function relationship, and temporal network evolution to distill valuable information embedded in the gene functional interactions in literature. We demonstrate the application of the proposed framework using a testbed of P53-related PubMed abstracts, which shows that literature-based P53 networks exhibit small-world and scale-free properties. We also found that high degree genes in the literature-based networks have a high probability of appearing in the manually curated database and genes in the same pathway tend to form local clusters in our literature-based networks. Temporal analysis showed that genes interacting with many other genes tend to be involved in a large number of newly discovered interactions.
In an online shopping platform, a detailed classification of the products facilitates user navigation. It also helps online retailers keep track of the price fluctuations in a certain industry or special discounts on a specific product category. Moreover, an automated classification system may help to pinpoint incorrect or subjective categories suggested by an operator. In this study, we focus on product title classification of the grocery products. We perform a comprehensive comparison of six different text classification models to establish a strong baseline for this task, which involves testing both traditional and recent machine learning methods. In our experiments, we investigate the generalizability of the trained models to the products of other online retailers, the dynamic masking of infeasible subcategories for pretrained language models, and the benefits of incorporating product titles in multiple languages. Our numerical results indicate that dynamic masking of subcategories is effective in improving prediction accuracy. In addition, we observe that using bilingual product titles is generally beneficial, and neural network-based models perform significantly better than SVM and XGBoost models. Lastly, we investigate the reasons for the misclassified products and propose future research directions to further enhance the prediction models.
We present the Eyetracked Multi-Modal Translation (EMMT) corpus, a dataset containing monocular eye movement recordings, audio and 4-electrode electroencephalogram (EEG) data of 43 participants. The objective was to collect cognitive signals as responses of participants engaged in a number of language intensive tasks involving different text-image stimuli settings when translating from English to Czech. Each participant was exposed to 32 text-image stimuli pairs and asked to (1) read the English sentence, (2) translate it into Czech, (3) consult the image, (4) translate again, either updating or repeating the previous translation. The text stimuli consisted of 200 unique sentences with 616 unique words coupled with 200 unique images as the visual stimuli. The recordings were collected over a two week period and all the participants included in the study were Czech natives with strong English skills. Due to the nature of the tasks involved in the study and the relatively large number of participants involved, the corpus is well suited for research in Translation Process Studies, Cognitive Sciences among other disciplines.
With the burgeoning amount of data of image-text pairs and diversity of Vision-and-Language (V&L) tasks, scholars have introduced an abundance of deep learning models in this research domain. Furthermore, in recent years, transfer learning has also shown tremendous success in Computer Vision for tasks such as Image Classification, Object Detection, etc., and in Natural Language Processing for Question Answering, Machine Translation, etc. Inheriting the spirit of Transfer Learning, research works in V&L have devised multiple pretraining techniques on large-scale datasets in order to enhance the performance of downstream tasks. The aim of this article is to provide a comprehensive revision of contemporary V&L pretraining models. In particular, we categorize and delineate pretraining approaches, along with the summary of state-of-the-art vision-and-language pre-trained models. Moreover, a list of training datasets and downstream tasks is supplied to further polish the perspective on V&L pretraining. Lastly, we decided to take a further step to discuss numerous directions for future research.
Generating text from structured inputs, such as meaning representations or RDF triples, has often involved the use of specialized graph-encoding neural networks. However, recent applications of pretrained transformers to linearizations of graph inputs have yielded state-of-the-art generation results on graph-to-text tasks. Here, we explore the ability of these linearized models to encode local graph structures, in particular their invariance to the graph linearization strategy and their ability to reconstruct corrupted inputs. Our findings motivate solutions to enrich the quality of models' implicit graph encodings via scaffolding. Namely, we use graph-denoising objectives implemented in a multi-task text-to-text framework. We find that these denoising scaffolds lead to substantial improvements in downstream generation in low-resource settings.