We present WikiReading, a large-scale natural language understanding task and publicly-available dataset with 18 million instances. The task is to predict textual values from the structured knowledge base Wikidata by reading the text of the corresponding Wikipedia articles. The task contains a rich variety of challenging classification and extraction sub-tasks, making it well-suited for end-to-end models such as deep neural networks (DNNs). We compare various state-of-the-art DNN-based architectures for document classification, information extraction, and question answering. We find that models supporting a rich answer space, such as word or character sequences, perform best. Our best-performing model, a word-level sequence to sequence model with a mechanism to copy out-of-vocabulary words, obtains an accuracy of 71.8%.
Commercial establishments like restaurants, service centres and retailers have several sources of customer feedback about products and services, most of which need not be as structured as rated reviews provided by services like Yelp, or Amazon, in terms of sentiment conveyed. For instance, Amazon provides a fine-grained score on a numeric scale for product reviews. Some sources, however, like social media (Twitter, Facebook), mailing lists (Google Groups) and forums (Quora) contain text data that is much more voluminous, but unstructured and unlabelled. It might be in the best interests of a business establishment to assess the general sentiment towards their brand on these platforms as well. This text could be pipelined into a system with a built-in prediction model, with the objective of generating real-time graphs on opinion and sentiment trends. Although such tasks like the one described about have been explored with respect to document classification problems in the past, the implementation described in this paper, by virtue of learning a continuous function rather than a discrete one, offers a lot more depth of insight as compared to document classification approaches. This study aims to explore the validity of such a continuous function predicting model to quantify sentiment about an entity, without the additional overhead of manual labelling, and computational preprocessing & feature extraction. This research project also aims to design and implement a re-usable document regression pipeline as a framework, Rapid-Rate, that can be used to predict document scores in real-time.
Recurrent Neural Networks are showing much promise in many sub-areas of natural language processing, ranging from document classification to machine translation to automatic question answering. Despite their promise, many recurrent models have to read the whole text word by word, making it slow to handle long documents. For example, it is difficult to use a recurrent network to read a book and answer questions about it. In this paper, we present an approach of reading text while skipping irrelevant information if needed. The underlying model is a recurrent network that learns how far to jump after reading a few words of the input text. We employ a standard policy gradient method to train the model to make discrete jumping decisions. In our benchmarks on four different tasks, including number prediction, sentiment analysis, news article classification and automatic Q\&A, our proposed model, a modified LSTM with jumping, is up to 6 times faster than the standard sequential LSTM, while maintaining the same or even better accuracy.
In this paper, we explore SPPIM-based text classification method, and the experiment reveals that the SPPIM method is equal to or even superior than SGNS method in text classification task on three international and standard text datasets, namely 20newsgroups, Reuters52 and WebKB. Comparing to SGNS, although SPPMI provides a better solution, it is not necessarily better than SGNS in text classification tasks. Based on our analysis, SGNS takes into the consideration of weight calculation during decomposition process, so it has better performance than SPPIM in some standard datasets. Inspired by this, we propose a WL-SPPIM semantic model based on SPPIM model, and experiment shows that WL-SPPIM approach has better classification and higher scalability in the text classification task compared with LDA, SGNS and SPPIM approaches.
We investigate the pertinence of methods from algebraic topology for text data analysis. These methods enable the development of mathematically-principled isometric-invariant mappings from a set of vectors to a document embedding, which is stable with respect to the geometry of the document in the selected metric space. In this work, we evaluate the utility of these topology-based document representations in traditional NLP tasks, specifically document clustering and sentiment classification. We find that the embeddings do not benefit text analysis. In fact, performance is worse than simple techniques like $\textit{tf-idf}$, indicating that the geometry of the document does not provide enough variability for classification on the basis of topic or sentiment in the chosen datasets.
Autoencoders have been successful in learning meaningful representations from image datasets. However, their performance on text datasets has not been widely studied. Traditional autoencoders tend to learn possibly trivial representations of text documents due to their confounding properties such as high-dimensionality, sparsity and power-law word distributions. In this paper, we propose a novel k-competitive autoencoder, called KATE, for text documents. Due to the competition between the neurons in the hidden layer, each neuron becomes specialized in recognizing specific data patterns, and overall the model can learn meaningful representations of textual data. A comprehensive set of experiments show that KATE can learn better representations than traditional autoencoders including denoising, contractive, variational, and k-sparse autoencoders. Our model also outperforms deep generative models, probabilistic topic models, and even word representation models (e.g., Word2Vec) in terms of several downstream tasks such as document classification, regression, and retrieval.
Correlated topic modeling has been limited to small model and problem sizes due to their high computational cost and poor scaling. In this paper, we propose a new model which learns compact topic embeddings and captures topic correlations through the closeness between the topic vectors. Our method enables efficient inference in the low-dimensional embedding space, reducing previous cubic or quadratic time complexity to linear w.r.t the topic size. We further speedup variational inference with a fast sampler to exploit sparsity of topic occurrence. Extensive experiments show that our approach is capable of handling model and data scales which are several orders of magnitude larger than existing correlation results, without sacrificing modeling quality by providing competitive or superior performance in document classification and retrieval.
In this paper we perform a comparative analysis of three models for feature representation of text documents in the context of document classification. In particular, we consider the most often used family of models bag-of-words, recently proposed continuous space models word2vec and doc2vec, and the model based on the representation of text documents as language networks. While the bag-of-word models have been extensively used for the document classification task, the performance of the other two models for the same task have not been well understood. This is especially true for the network-based model that have been rarely considered for representation of text documents for classification. In this study, we measure the performance of the document classifiers trained using the method of random forests for features generated the three models and their variants. The results of the empirical comparison show that the commonly used bag-of-words model has performance comparable to the one obtained by the emerging continuous-space model of doc2vec. In particular, the low-dimensional variants of doc2vec generating up to 75 features are among the top-performing document representation models. The results finally point out that doc2vec shows a superior performance in the tasks of classifying large documents.
We present an efficient document representation learning framework, Document Vector through Corruption (Doc2VecC). Doc2VecC represents each document as a simple average of word embeddings. It ensures a representation generated as such captures the semantic meanings of the document during learning. A corruption model is included, which introduces a data-dependent regularization that favors informative or rare words while forcing the embeddings of common and non-discriminative ones to be close to zero. Doc2VecC produces significantly better word embeddings than Word2Vec. We compare Doc2VecC with several state-of-the-art document representation learning algorithms. The simple model architecture introduced by Doc2VecC matches or out-performs the state-of-the-art in generating high-quality document representations for sentiment analysis, document classification as well as semantic relatedness tasks. The simplicity of the model enables training on billions of words per hour on a single machine. At the same time, the model is very efficient in generating representations of unseen documents at test time.
Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications. We discover that modern neural networks, unlike those from a decade ago, are poorly calibrated. Through extensive experiments, we observe that depth, width, weight decay, and Batch Normalization are important factors influencing calibration. We evaluate the performance of various post-processing calibration methods on state-of-the-art architectures with image and document classification datasets. Our analysis and experiments not only offer insights into neural network learning, but also provide a simple and straightforward recipe for practical settings: on most datasets, temperature scaling -- a single-parameter variant of Platt Scaling -- is surprisingly effective at calibrating predictions.
While there have been significant advances in detecting emotions from speech and image recognition, emotion detection on text is still under-explored and remained as an active research field. This paper introduces a corpus for text-based emotion detection on multiparty dialogue as well as deep neural models that outperform the existing approaches for document classification. We first present a new corpus that provides annotation of seven emotions on consecutive utterances in dialogues extracted from the show, Friends. We then suggest four types of sequence-based convolutional neural network models with attention that leverage the sequence information encapsulated in dialogue. Our best model shows the accuracies of 37.9% and 54% for fine- and coarse-grained emotions, respectively. Given the difficulty of this task, this is promising.
The success of any machine learning system depends critically on effective representations of data. In many cases, it is desirable that a representation scheme uncovers the parts-based, additive nature of the data. Of current representation learning schemes, restricted Boltzmann machines (RBMs) have proved to be highly effective in unsupervised settings. However, when it comes to parts-based discovery, RBMs do not usually produce satisfactory results. We enhance such capacity of RBMs by introducing nonnegativity into the model weights, resulting in a variant called nonnegative restricted Boltzmann machine (NRBM). The NRBM produces not only controllable decomposition of data into interpretable parts but also offers a way to estimate the intrinsic nonlinear dimensionality of data, and helps to stabilize linear predictive models. We demonstrate the capacity of our model on applications such as handwritten digit recognition, face recognition, document classification and patient readmission prognosis. The decomposition quality on images is comparable with or better than what produced by the nonnegative matrix factorization (NMF), and the thematic features uncovered from text are qualitatively interpretable in a similar manner to that of the latent Dirichlet allocation (LDA). The stability performance of feature selection on medical data is better than RBM and competitive with NMF. The learned features, when used for classification, are more discriminative than those discovered by both NMF and LDA and comparable with those by RBM.
Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language entails linear parameter growth and lack of cross-language transfer. Learning a single multilingual model with fewer parameters is therefore a challenging but potentially beneficial objective. To this end, we propose multilingual hierarchical attention networks for learning document structures, with shared encoders and/or shared attention mechanisms across languages, using multi-task learning and an aligned semantic space as input. We evaluate the proposed models on multilingual document classification with disjoint label sets, on a large dataset which we provide, with 600k news documents in 8 languages, and 5k labels. The multilingual models outperform monolingual ones in low-resource as well as full-resource settings, and use fewer parameters, thus confirming their computational efficiency and the utility of cross-language transfer.
A significant part of the largest Knowledge Graph today, the Linked Open Data cloud, consists of metadata about documents such as publications, news reports, and other media articles. While the widespread access to the document metadata is a tremendous advancement, it is yet not so easy to assign semantic annotations and organize the documents along semantic concepts. Providing semantic annotations like concepts in SKOS thesauri is a classical research topic, but typically it is conducted on the full-text of the documents. For the first time, we offer a systematic comparison of classification approaches to investigate how far semantic annotations can be conducted using just the metadata of the documents such as titles published as labels on the Linked Open Data cloud. We compare the classifications obtained from analyzing the documents' titles with semantic annotations obtained from analyzing the full-text. Apart from the prominent text classification baselines kNN and SVM, we also compare recent techniques of Learning to Rank and neural networks and revisit the traditional methods logistic regression, Rocchio, and Naive Bayes. The results show that across three of our four datasets, the performance of the classifications using only titles reaches over 90% of the quality compared to the classification performance when using the full-text. Thus, conducting document classification by just using the titles is a reasonable approach for automated semantic annotation and opens up new possibilities for enriching Knowledge Graphs.
The continually increasing number of documents produced each year necessitates ever improving information processing methods for searching, retrieving, and organizing text. Central to these information processing methods is document classification, which has become an important application for supervised learning. Recently the performance of these traditional classifiers has degraded as the number of documents has increased. This is because along with this growth in the number of documents has come an increase in the number of categories. This paper approaches this problem differently from current document classification methods that view the problem as multi-class classification. Instead we perform hierarchical classification using an approach we call Hierarchical Deep Learning for Text classification (HDLTex). HDLTex employs stacks of deep learning architectures to provide specialized understanding at each level of the document hierarchy.
This paper presents an approach for real-time training and testing for document image classification. In production environments, it is crucial to perform accurate and (time-)efficient training. Existing deep learning approaches for classifying documents do not meet these requirements, as they require much time for training and fine-tuning the deep architectures. Motivated from Computer Vision, we propose a two-stage approach. The first stage trains a deep network that works as feature extractor and in the second stage, Extreme Learning Machines (ELMs) are used for classification. The proposed approach outperforms all previously reported structural and deep learning based methods with a final accuracy of 83.24% on Tobacco-3482 dataset, leading to a relative error reduction of 25% when compared to a previous Convolutional Neural Network (CNN) based approach (DeepDocClassifier). More importantly, the training time of the ELM is only 1.176 seconds and the overall prediction time for 2,482 images is 3.066 seconds. As such, this novel approach makes deep learning-based document classification suitable for large-scale real-time applications.
Data mining, machine learning, and natural language processing are powerful techniques that can be used together to extract information from large texts. Depending on the task or problem at hand, there are many different approaches that can be used. The methods available are continuously being optimized, but not all these methods have been tested and compared in a set of problems that can be solved using supervised machine learning algorithms. The question is what happens to the quality of the methods if we increase the training data size from, say, 100 MB to over 1 GB? Moreover, are quality gains worth it when the rate of data processing diminishes? Can we trade quality for time efficiency and recover the quality loss by just being able to process more data? We attempt to answer these questions in a general way for text processing tasks, considering the trade-offs involving training data size, learning time, and quality obtained. We propose a performance trade-off framework and apply it to three important text processing problems: Named Entity Recognition, Sentiment Analysis and Document Classification. These problems were also chosen because they have different levels of object granularity: words, paragraphs, and documents. For each problem, we selected several supervised machine learning algorithms and we evaluated the trade-offs of them on large publicly available data sets (news, reviews, patents). To explore these trade-offs, we use different data subsets of increasing size ranging from 50 MB to several GB. We also consider the impact of the data set and the evaluation technique. We find that the results do not change significantly and that most of the time the best algorithms is the fastest. However, we also show that the results for small data (say less than 100 MB) are different from the results for big data and in those cases the best algorithm is much harder to determine.
This paper introduces "Czech Text Document Corpus v 2.0", a collection of text documents for automatic document classification in Czech language. It is composed of the text documents provided by the Czech News Agency and is freely available for research purposes at http://ctdc.kiv.zcu.cz/. This corpus was created in order to facilitate a straightforward comparison of the document classification approaches on Czech data. It is particularly dedicated to evaluation of multi-label document classification approaches, because one document is usually labelled with more than one label. Besides the information about the document classes, the corpus is also annotated at the morphological layer. This paper further shows the results of selected state-of-the-art methods on this corpus to offer the possibility of an easy comparison with these approaches.
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).
It is a usual practice to ignore any structural information underlying classes in multi-class classification. In this paper, we propose a graph convolutional network (GCN) augmented neural network classifier to exploit a known, underlying graph structure of labels. The proposed approach resembles an (approximate) inference procedure in, for instance, a conditional random field (CRF). We evaluate the proposed approach on document classification and object recognition and report both accuracies and graph-theoretic metrics that correspond to the consistency of the model's prediction. The experiment results reveal that the proposed model outperforms a baseline method which ignores the graph structures of a label space in terms of graph-theoretic metrics.