This paper presents a study showing the benefits of the EfficientNet models compared with heavier Convolutional Neural Networks (CNNs) in the Document Classification task, essential problem in the digitalization process of institutions. We show in the RVL-CDIP dataset that we can improve previous results with a much lighter model and present its transfer learning capabilities on a smaller in-domain dataset such as Tobacco3482. Moreover, we present an ensemble pipeline which is able to boost solely image input by combining image model predictions with the ones generated by BERT model on extracted text by OCR. We also show that the batch size can be effectively increased without hindering its accuracy so that the training process can be sped up by parallelizing throughout multiple GPUs, decreasing the computational time needed. Lastly, we expose the training performance differences between PyTorch and Tensorflow Deep Learning frameworks.
A rapid growth of web documents due to heavy use of World Wide Web necessitates efficient techniques to efficiently classify the document on the web. It is thus produced High volumes of data per second with high diversity. Automatically classification of these growing amounts of web document is One of the biggest challenges facing us today. Probabilistic classification algorithms such as Naive Bayes have become commonly used for web document classification. This problem is mainly because of the irrelatively high classification accuracy on plenty application areas as well as their lack of support to handle high dimensional and sparse data which is the exclusive characteristics of textual data representation. also it is common to Lack of attention and support the semantic relation between words using traditional feature selection method When dealing with the big data and large-scale web documents. In order to solve the problem, we proposed a method for web document classification that uses LSA to increase similarity of documents under the same class and improve the classification precision. Using this approach, we designed a faster and much accurate classifier for Web Documents. Experimental results have shown that using the mentioned preprocessing can improve accuracy and speed of Naive Bayes availably, the precision and recall metrics have indicated the improvement.
Due to the increasing amount of data on the internet, finding a highly-informative, low-dimensional representation for text is one of the main challenges for efficient natural language processing tasks including text classification. This representation should capture the semantic information of the text while retaining their relevance level for document classification. This approach maps the documents with similar topics to a similar space in vector space representation. To obtain representation for large text, we propose the utilization of deep Siamese neural networks. To embed document relevance in topics in the distributed representation, we use a Siamese neural network to jointly learn document representations. Our Siamese network consists of two sub-network of multi-layer perceptron. We examine our representation for the text categorization task on BBC news dataset. The results show that the proposed representations outperform the conventional and state-of-the-art representations in the text classification task on this dataset.
Pre-training large-scale neural language models on raw texts has made a significant contribution to improving transfer learning in natural language processing (NLP). With the introduction of transformer-based language models, such as bidirectional encoder representations from transformers (BERT), the performance of information extraction from a free text by NLP has significantly improved for both the general domain and medical domain; however, it is difficult to train specific BERT models that perform well for domains in which there are few publicly available databases of high quality and large size. We hypothesized that this problem can be addressed by up-sampling a domain-specific corpus and using it for pre-training with a larger corpus in a balanced manner. Our proposed method consists of a single intervention with one option: simultaneous pre-training after up-sampling and amplified vocabulary. We conducted three experiments and evaluated the resulting products. We confirmed that our Japanese medical BERT outperformed conventional baselines and the other BERT models in terms of the medical document classification task and that our English BERT pre-trained using both the general and medical-domain corpora performed sufficiently well for practical use in terms of the biomedical language understanding evaluation (BLUE) benchmark. Moreover, our enhanced biomedical BERT model, in which clinical notes were not used during pre-training, showed that both the clinical and biomedical scores of the BLUE benchmark were 0.3 points above that of the ablation model trained without our proposed method. Well-balanced pre-training by up-sampling instances derived from a corpus appropriate for the target task allows us to construct a high-performance BERT model.
Document categorization, which aims to assign a topic label to each document, plays a fundamental role in a wide variety of applications. Despite the success of existing studies in conventional supervised document classification, they are less concerned with two real problems: (1) the presence of metadata: in many domains, text is accompanied by various additional information such as authors and tags. Such metadata serve as compelling topic indicators and should be leveraged into the categorization framework; (2) label scarcity: labeled training samples are expensive to obtain in some cases, where categorization needs to be performed using only a small set of annotated data. In recognition of these two challenges, we propose MetaCat, a minimally supervised framework to categorize text with metadata. Specifically, we develop a generative process describing the relationships between words, documents, labels, and metadata. Guided by the generative model, we embed text and metadata into the same semantic space to encode heterogeneous signals. Then, based on the same generative process, we synthesize training samples to address the bottleneck of label scarcity. We conduct a thorough evaluation on a wide range of datasets. Experimental results prove the effectiveness of MetaCat over many competitive baselines.
This paper presents a reinforcement learning approach to extract noise in long clinical documents for the task of readmission prediction after kidney transplant. We face the challenges of developing robust models on a small dataset where each document may consist of over 10K tokens with full of noise including tabular text and task-irrelevant sentences. We first experiment four types of encoders to empirically decide the best document representation, and then apply reinforcement learning to remove noisy text from the long documents, which models the noise extraction process as a sequential decision problem. Our results show that the old bag-of-words encoder outperforms deep learning-based encoders on this task, and reinforcement learning is able to improve upon baseline while pruning out 25% text segments. Our analysis depicts that reinforcement learning is able to identify both typical noisy tokens and task-specific noisy text.
Document classification is ubiquitous in a business setting, but often the end users of a classifier are engaged in an ongoing feedback-retrain loop with the team that maintain it. We consider this feedback-retrain loop from a multi-agent point of view, considering the end users as autonomous agents that provide feedback on the labelled data provided by the classifier. This allows us to examine the effect on the classifier's performance of unreliable end users who provide incorrect feedback. We demonstrate a classifier that can learn which users tend to be unreliable, filtering their feedback out of the loop, thus improving performance in subsequent iterations.
Using attention weights to identify information that is important for models' decision-making is a popular approach to interpret attention-based neural networks. This is commonly realized in practice through the generation of a heat-map for every single document based on attention weights. However, this interpretation method is fragile, and easy to find contradictory examples. In this paper, we propose a corpus-level explanation approach, which aims to capture causal relationships between keywords and model predictions via learning the importance of keywords for predicted labels across a training corpus based on attention weights. Based on this idea, we further propose a concept-based explanation method that can automatically learn higher-level concepts and their importance to model prediction tasks. Our concept-based explanation method is built upon a novel Abstraction-Aggregation Network, which can automatically cluster important keywords during an end-to-end training process. We apply these methods to the document classification task and show that they are powerful in extracting semantically meaningful keywords and concepts. Our consistency analysis results based on an attention-based Na\"ive Bayes classifier also demonstrate these keywords and concepts are important for model predictions.
Organisations disclose their privacy practices by posting privacy policies on their website. Even though users often care about their digital privacy, they often don't read privacy policies since they require a significant investment in time and effort. Although natural language processing can help in privacy policy understanding, there has been a lack of large scale privacy policy corpora that could be used to analyse, understand, and simplify privacy policies. Thus, we create PrivaSeer, a corpus of over one million English language website privacy policies, which is significantly larger than any previously available corpus. We design a corpus creation pipeline which consists of crawling the web followed by filtering documents using language detection, document classification, duplicate and near-duplication removal, and content extraction. We investigate the composition of the corpus and show results from readability tests, document similarity, keyphrase extraction, and explored the corpus through topic modeling.
For management, documents are categorized into a specific category, and to do these, most of the organizations use manual labor. In today's automation era, manual efforts on such a task are not justified, and to avoid this, we have so many software out there in the market. However, efficiency and minimal resource consumption is the focal point which is also creating a competition. The categorization of such documents into specified classes by machine provides excellent help. One of categorization technique is text classification using a Convolutional neural network(TextCNN). TextCNN uses multiple sizes of filters, as in the case of the inception layer introduced in Googlenet. The network provides good accuracy but causes high memory consumption due to a large number of trainable parameters. As a solution to this problem, we introduced a whole new architecture based on separable convolution. The idea of separable convolution already exists in the field of image classification but not yet introduces to text classification tasks. With the help of this architecture, we can achieve a drastic reduction in trainable parameters.
Exponential growths of social media and micro-blogging sites not only provide platforms for empowering freedom of expressions and individual voices but also enables people to express anti-social behaviour like online harassment, cyberbullying, and hate speech. Numerous works have been proposed to utilize these data for social and anti-social behaviours analysis, document characterization, and sentiment analysis by predicting the contexts mostly for highly resourced languages such as English. However, there are languages that are under-resources, e.g., South Asian languages like Bengali, Tamil, Assamese, Telugu that lack of computational resources for the NLP tasks. In this paper, we provide several classification benchmarks for Bengali, an under-resourced language. We prepared three datasets of expressing hate, commonly used topics, and opinions for hate speech detection, document classification, and sentiment analysis, respectively. We built the largest Bengali word embedding models to date based on 250 million articles, which we call BengFastText. We perform three different experiments, covering document classification, sentiment analysis, and hate speech detection. We incorporate word embeddings into a Multichannel Convolutional-LSTM (MConv-LSTM) network for predicting different types of hate speech, document classification, and sentiment analysis. Experiments demonstrate that BengFastText can capture the semantics of words from respective contexts correctly. Evaluations against several baseline embedding models, e.g., Word2Vec and GloVe yield up to 92.30%, 82.25%, and 90.45% F1-scores in case of document classification, sentiment analysis, and hate speech detection, respectively during 5-fold cross-validation tests.
Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level training objectives and do not leverage information on inter-document relatedness, which limits their document-level representation power. For applications on scientific documents, such as classification and recommendation, the embeddings power strong performance on end tasks. We propose SPECTER, a new method to generate document-level embedding of scientific documents based on pretraining a Transformer language model on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language models, SPECTER can be easily applied to downstream applications without task-specific fine-tuning. Additionally, to encourage further research on document-level models, we introduce SciDocs, a new evaluation benchmark consisting of seven document-level tasks ranging from citation prediction, to document classification and recommendation. We show that SPECTER outperforms a variety of competitive baselines on the benchmark.
Analyzing the ever-increasing volume of posts on social media sites such as Facebook and Twitter requires improved information processing methods for profiling authorship. Document classification is central to this task, but the performance of traditional supervised classifiers has degraded as the volume of social media has increased. This paper addresses this problem in the context of gender detection through ensemble classification that employs multi-model deep learning architectures to generate specialized understanding from different feature spaces.
Recent progress on unsupervised learning of cross-lingual embeddings in bilingual setting has given impetus to learning a shared embedding space for several languages without any supervision. A popular framework to solve the latter problem is to jointly solve the following two sub-problems: 1) learning unsupervised word alignment between several pairs of languages, and 2) learning how to map the monolingual embeddings of every language to a shared multilingual space. In contrast, we propose a simple, two-stage framework in which we decouple the above two sub-problems and solve them separately using existing techniques. The proposed approach obtains surprisingly good performance in various tasks such as bilingual lexicon induction, cross-lingual word similarity, multilingual document classification, and multilingual dependency parsing. When distant languages are involved, the proposed solution illustrates robustness and outperforms existing unsupervised multilingual word embedding approaches. Overall, our experimental results encourage development of multi-stage models for such challenging problems.
In recent years, fully automated content analysis based on probabilistic topic models has become popular among social scientists because of their scalability. The unsupervised nature of the models makes them suitable for exploring topics in a corpus without prior knowledge. However, researchers find that these models often fail to measure specific concepts of substantive interest by inadvertently creating multiple topics with similar content and combining distinct themes into a single topic. In this paper, we empirically demonstrate that providing a small number of keywords can substantially enhance the measurement performance of topic models. An important advantage of the proposed keyword assisted topic model (keyATM) is that the specification of keywords requires researchers to label topics prior to fitting a model to the data. This contrasts with a widespread practice of post-hoc topic interpretation and adjustments that compromises the objectivity of empirical findings. In our application, we find that keyATM provides more interpretable results, has better document classification performance, and is less sensitive to the number of topics than the standard topic models. Finally, we show that keyATM can also incorporate covariates and model time trends. An open-source software package is available for implementing the proposed methodology.
This paper introduces and evaluates two novel Hierarchical Attention Network models [Yang et al., 2016] - i) Hierarchical Pruned Attention Networks, which remove the irrelevant words and sentences from the classification process in order to reduce potential noise in the document classification accuracy and ii) Hierarchical Sparsemax Attention Networks, which replace the Softmax function used in the attention mechanism with the Sparsemax [Martins and Astudillo, 2016], capable of better handling importance distributions where a lot of words or sentences have very low probabilities. Our empirical evaluation on the IMDB Review for sentiment analysis datasets shows both approaches to be able to match the results obtained by the current state-of-the-art (without, however, any significant benefits). All our source code is made available athttps://github.com/jmribeiro/dsl-project.
Vast volumes of printed documents continue to be used for various important as well as trivial applications. Such applications often rely on the information provided in the form of printed text documents whose integrity verification poses a challenge due to time constraints and lack of resources. Source printer identification provides essential information about the origin and integrity of a printed document in a fast and cost-effective manner. Even when fraudulent documents are identified, information about their origin can help stop future frauds. If a smartphone camera replaces scanner for the document acquisition process, document forensics would be more economical, user-friendly, and even faster in many applications where remote and distributed analysis is beneficial. Building on existing methods, we propose to learn a single CNN model from the fusion of letter images and their printer-specific noise residuals. In the absence of any publicly available dataset, we created a new dataset consisting of 2250 document images of text documents printed by eighteen printers and acquired by a smartphone camera at five acquisition settings. The proposed method achieves 98.42% document classification accuracy using images of letter 'e' under a 5x2 cross-validation approach. Further, when tested using about half a million letters of all types, it achieves 90.33% and 98.01% letter and document classification accuracies, respectively, thus highlighting the ability to learn a discriminative model without dependence on a single letter type. Also, classification accuracies are encouraging under various acquisition settings, including low illumination and change in angle between the document and camera planes.
Many digital libraries recommend literature to their users considering the similarity between a query document and their repository. However, they often fail to distinguish what is the relationship that makes two documents alike. In this paper, we model the problem of finding the relationship between two documents as a pairwise document classification task. To find the semantic relation between documents, we apply a series of techniques, such as GloVe, Paragraph-Vectors, BERT, and XLNet under different configurations (e.g., sequence length, vector concatenation scheme), including a Siamese architecture for the Transformer-based systems. We perform our experiments on a newly proposed dataset of 32,168 Wikipedia article pairs and Wikidata properties that define the semantic document relations. Our results show vanilla BERT as the best performing system with an F1-score of 0.93, which we manually examine to better understand its applicability to other domains. Our findings suggest that classifying semantic relations between documents is a solvable task and motivates the development of recommender systems based on the evaluated techniques. The discussions in this paper serve as first steps in the exploration of documents through SPARQL-like queries such that one could find documents that are similar in one aspect but dissimilar in another.
Since the seminal work of Mikolov et al., word embeddings have become the preferred word representations for many natural language processing tasks. Document similarity measures extracted from word embeddings, such as the soft cosine measure (SCM) and the Word Mover's Distance (WMD), were reported to achieve state-of-the-art performance on semantic text similarity and text classification. Despite the strong performance of the WMD on text classification and semantic text similarity, its super-cubic average time complexity is impractical. The SCM has quadratic worst-case time complexity, but its performance on text classification has never been compared with the WMD. Recently, two word embedding regularization techniques were shown to reduce storage and memory costs, and to improve training speed, document processing speed, and task performance on word analogy, word similarity, and semantic text similarity. However, the effect of these techniques on text classification has not yet been studied. In our work, we investigate the individual and joint effect of the two word embedding regularization techniques on the document processing speed and the task performance of the SCM and the WMD on text classification. For evaluation, we use the $k$NN classifier and six standard datasets: BBCSPORT, TWITTER, OHSUMED, REUTERS-21578, AMAZON, and 20NEWS. We show 39% average $k$NN test error reduction with regularized word embeddings compared to non-regularized word embeddings. We describe a practical procedure for deriving such regularized embeddings through Cholesky factorization. We also show that the SCM with regularized word embeddings significantly outperforms the WMD on text classification and is over 10,000 times faster.
The input to the \emph{sets-$k$-means} problem is an integer $k\geq 1$ and a set $\mathcal{P}=\{P_1,\cdots,P_n\}$ of sets in $\mathbb{R}^d$. The goal is to compute a set $C$ of $k$ centers (points) in $\mathbb{R}^d$ that minimizes the sum $\sum_{P\in \mathcal{P}} \min_{p\in P, c\in C}\left\| p-c \right\|^2$ of squared distances to these sets. An \emph{$\varepsilon$-core-set} for this problem is a weighted subset of $\mathcal{P}$ that approximates this sum up to $1\pm\varepsilon$ factor, for \emph{every} set $C$ of $k$ centers in $\mathbb{R}^d$. We prove that such a core-set of $O(\log^2{n})$ sets always exists, and can be computed in $O(n\log{n})$ time, for every input $\mathcal{P}$ and every fixed $d,k\geq 1$ and $\varepsilon \in (0,1)$. The result easily generalized for any metric space, distances to the power of $z>0$, and M-estimators that handle outliers. Applying an inefficient but optimal algorithm on this coreset allows us to obtain the first PTAS ($1+\varepsilon$ approximation) for the sets-$k$-means problem that takes time near linear in $n$. This is the first result even for sets-mean on the plane ($k=1$, $d=2$). Open source code and experimental results for document classification and facility locations are also provided.