Dominant pre-training work for video-text retrieval mainly adopt the "dual-encoder" architectures to enable efficient retrieval, where two separate encoders are used to contrast global video and text representations, but ignore detailed local semantics. The recent success of image BERT pre-training with masked visual modeling that promotes the learning of local visual context, motivates a possible solution to address the above limitation. In this work, we for the first time investigate masked visual modeling in video-text pre-training with the "dual-encoder" architecture. We perform Masked visual modeling with Injected LanguagE Semantics (MILES) by employing an extra snapshot video encoder as an evolving "tokenizer" to produce reconstruction targets for masked video patch prediction. Given the corrupted video, the video encoder is trained to recover text-aligned features of the masked patches via reasoning with the visible regions along the spatial and temporal dimensions, which enhances the discriminativeness of local visual features and the fine-grained cross-modality alignment. Our method outperforms state-of-the-art methods for text-to-video retrieval on four datasets with both zero-shot and fine-tune evaluation protocols. Our approach also surpasses the baseline models significantly on zero-shot action recognition, which can be cast as video-to-text retrieval.
Linking authors of short-text contents has important usages in many applications, including Named Entity Recognition (NER) and human community detection. However, certain challenges lie ahead. Firstly, the input short-text contents are noisy, ambiguous, and do not follow the grammatical rules. Secondly, traditional text mining methods fail to effectively extract concepts through words and phrases. Thirdly, the textual contents are temporally skewed, which can affect the semantic understanding by multiple time facets. Finally, using the complementary knowledge-bases makes the results biased to the content of the external database and deviates the understanding and interpretation away from the real nature of the given short text corpus. To overcome these challenges, we devise a neural network-based temporal-textual framework that generates the tightly connected author subgraphs from microblog short-text contents. Our approach, on the one hand, computes the relevance score (edge weight) between the authors through considering a portmanteau of contents and concepts, and on the other hand, employs a stack-wise graph cutting algorithm to extract the communities of the related authors. Experimental results show that compared to other knowledge-centered competitors, our multi-aspect vector space model can achieve a higher performance in linking short-text authors. Additionally, given the author linking task, the more comprehensive the dataset is, the higher the significance of the extracted concepts will be.
A text steganography method based on Markov chains is introduced, together with a reference implementation. This method allows for information hiding in texts that are automatically generated following a given Markov model. Other Markov - based systems of this kind rely on big simplifications of the language model to work, which produces less natural looking and more easily detectable texts. The method described here is designed to generate texts within a good approximation of the original language model provided.
The bag-of-words model is a standard representation of text for many linear classifier learners. In many problem domains, linear classifiers are preferred over more complex models due to their efficiency, robustness and interpretability, and the bag-of-words text representation can capture sufficient information for linear classifiers to make highly accurate predictions. However in settings where there is a large vocabulary, large variance in the frequency of terms in the training corpus, many classes and very short text (e.g., single sentences or document titles) the bag-of-words representation becomes extremely sparse, and this can reduce the accuracy of classifiers. A particular issue in such settings is that short texts tend to contain infrequently occurring or rare terms which lack class-conditional evidence. In this work we introduce a method for enriching the bag-of-words model by complementing such rare term information with related terms from both general and domain-specific Word Vector models. By reducing sparseness in the bag-of-words models, our enrichment approach achieves improved classification over several baseline classifiers in a variety of text classification problems. Our approach is also efficient because it requires no change to the linear classifier before or during training, since bag-of-words enrichment applies only to text being classified.
How people think, feel, and behave, primarily is a representation of their personality characteristics. By being conscious of personality characteristics of individuals whom we are dealing with or decided to deal with, one can competently ameliorate the relationship, regardless of its type. With the rise of Internet-based communication infrastructures (social networks, forums, etc.), a considerable amount of human communications take place there. The most prominent tool in such communications, is the language in written and spoken form that adroitly encodes all those essential personality characteristics of individuals. Text-based Automatic Personality Prediction (APP) is the automated forecasting of the personality of individuals based on the generated/exchanged text contents. This paper presents a novel knowledge graph-enabled approach to text-based APP that relies on the Big Five personality traits. To this end, given a text a knowledge graph which is a set of interlinked descriptions of concepts, was built through matching the input text's concepts with DBpedia knowledge base entries. Then, due to achieving more powerful representation the graph was enriched with the DBpedia ontology, NRC Emotion Intensity Lexicon, and MRC psycholinguistic database information. Afterwards, the knowledge graph which is now a knowledgeable alternative for the input text was embedded to yield an embedding matrix. Finally, to perform personality predictions the resulting embedding matrix was fed to four suggested deep learning models independently, which are based on convolutional neural network (CNN), simple recurrent neural network (RNN), long short term memory (LSTM) and bidirectional long short term memory (BiLSTM). The results indicated a considerable improvements in prediction accuracies in all of the suggested classifiers.
In the area of geographic information processing. There are few researches on geographic text classification. However, the application of this task in Chinese is relatively rare. In our work, we intend to implement a method to extract text containing geographical entities from a large number of network text. The geographic information in these texts is of great practical significance to transportation, urban and rural planning, disaster relief and other fields. We use the method of graph convolutional neural network with attention mechanism to achieve this function. Graph attention networks is an improvement of graph convolutional neural networks. Compared with GCN, the advantage of GAT is that the attention mechanism is proposed to weight the sum of the characteristics of adjacent nodes. In addition, We construct a Chinese dataset containing geographical classification from multiple datasets of Chinese text classification. The Macro-F Score of the geoGAT we used reached 95\% on the new Chinese dataset.
Recently multimodal named entity recognition (MNER) has utilized images to improve the accuracy of NER in tweets. However, most of the multimodal methods use attention mechanisms to extract visual clues regardless of whether the text and image are relevant. Practically, the irrelevant text-image pairs account for a large proportion in tweets. The visual clues that are unrelated to the texts will exert uncertain or even negative effects on multimodal model learning. In this paper, we introduce a method of text-image relation propagation into the multimodal BERT model. We integrate soft or hard gates to select visual clues and propose a multitask algorithm to train on the MNER datasets. In the experiments, we deeply analyze the changes in visual attention before and after the use of text-image relation propagation. Our model achieves state-of-the-art performance on the MNER datasets.
Deepfake detection, the task of automatically discriminating machine-generated text, is increasingly critical with recent advances in natural language generative models. Existing approaches to deepfake detection typically represent documents with coarse-grained representations. However, they struggle to capture factual structures of documents, which is a discriminative factor between machine-generated and human-written text according to our statistical analysis. To address this, we propose a graph-based model that utilizes the factual structure of a document for deepfake detection of text. Our approach represents the factual structure of a given document as an entity graph, which is further utilized to learn sentence representations with a graph neural network. Sentence representations are then composed to a document representation for making predictions, where consistent relations between neighboring sentences are sequentially modeled. Results of experiments on two public deepfake datasets show that our approach significantly improves strong base models built with RoBERTa. Model analysis further indicates that our model can distinguish the difference in the factual structure between machine-generated text and human-written text.
In this paper, we propose Double Supervised Network with Attention Mechanism (DSAN), a novel end-to-end trainable framework for scene text recognition. It incorporates one text attention module during feature extraction which enforces the model to focus on text regions and the whole framework is supervised by two branches. One supervision branch comes from context-level modelling and another comes from one extra supervision enhancement branch which aims at tackling inexplicit semantic information at character level. These two supervisions can benefit each other and yield better performance. The proposed approach can recognize text in arbitrary length and does not need any predefined lexicon. Our method outperforms the current state-of-the-art methods on three text recognition benchmarks: IIIT5K, ICDAR2013 and SVT reaching accuracy 88.6%, 92.3% and 84.1% respectively which suggests the effectiveness of the proposed method.
Hierarchical text classification, which aims to classify text documents into a given hierarchy, is an important task in many real-world applications. Recently, deep neural models are gaining increasing popularity for text classification due to their expressive power and minimum requirement for feature engineering. However, applying deep neural networks for hierarchical text classification remains challenging, because they heavily rely on a large amount of training data and meanwhile cannot easily determine appropriate levels of documents in the hierarchical setting. In this paper, we propose a weakly-supervised neural method for hierarchical text classification. Our method does not require a large amount of training data but requires only easy-to-provide weak supervision signals such as a few class-related documents or keywords. Our method effectively leverages such weak supervision signals to generate pseudo documents for model pre-training, and then performs self-training on real unlabeled data to iteratively refine the model. During the training process, our model features a hierarchical neural structure, which mimics the given hierarchy and is capable of determining the proper levels for documents with a blocking mechanism. Experiments on three datasets from different domains demonstrate the efficacy of our method compared with a comprehensive set of baselines.
Add to Chrome
Add to Firefox