LSHTC is a series of challenges which aims to assess the performance of classification systems in large-scale classification in a a large number of classes (up to hundreds of thousands). This paper describes the dataset that have been released along the LSHTC series. The paper details the construction of the datsets and the design of the tracks as well as the evaluation measures that we implemented and a quick overview of the results. All of these datasets are available online and runs may still be submitted on the online server of the challenges.
This paper proposes a methodology for generating a stopword list from online social network (OSN) corpora in Egyptian Dialect(ED). The aim of the paper is to investigate the effect of removingED stopwords on the Sentiment Analysis (SA) task. The stopwords lists generated before were on Modern Standard Arabic (MSA) which is not the common language used in OSN. We have generated a stopword list of Egyptian dialect to be used with the OSN corpora. We compare the efficiency of text classification when using the generated list along with previously generated lists of MSA and combining the Egyptian dialect list with the MSA list. The text classification was performed using Na\"ive Bayes and Decision Tree classifiers and two feature selection approaches, unigram and bigram. The experiments show that removing ED stopwords give better performance than using lists of MSA stopwords only.
This paper proposes a tree-based convolutional neural network (TBCNN) for discriminative sentence modeling. Our models leverage either constituency trees or dependency trees of sentences. The tree-based convolution process extracts sentences' structural features, and these features are aggregated by max pooling. Such architecture allows short propagation paths between the output layer and underlying feature detectors, which enables effective structural feature learning and extraction. We evaluate our models on two tasks: sentiment analysis and question classification. In both experiments, TBCNN outperforms previous state-of-the-art results, including existing neural networks and dedicated feature/rule engineering. We also make efforts to visualize the tree-based convolution process, shedding light on how our models work.
We define a family of probability distributions for random count matrices with a potentially unbounded number of rows and columns. The three distributions we consider are derived from the gamma-Poisson, gamma-negative binomial, and beta-negative binomial processes. Because the models lead to closed-form Gibbs sampling update equations, they are natural candidates for nonparametric Bayesian priors over count matrices. A key aspect of our analysis is the recognition that, although the random count matrices within the family are defined by a row-wise construction, their columns can be shown to be i.i.d. This fact is used to derive explicit formulas for drawing all the columns at once. Moreover, by analyzing these matrices' combinatorial structure, we describe how to sequentially construct a column-i.i.d. random count matrix one row at a time, and derive the predictive distribution of a new row count vector with previously unseen features. We describe the similarities and differences between the three priors, and argue that the greater flexibility of the gamma- and beta- negative binomial processes, especially their ability to model over-dispersed, heavy-tailed count data, makes these well suited to a wide variety of real-world applications. As an example of our framework, we construct a naive-Bayes text classifier to categorize a count vector to one of several existing random count matrices of different categories. The classifier supports an unbounded number of features, and unlike most existing methods, it does not require a predefined finite vocabulary to be shared by all the categories, and needs neither feature selection nor parameter tuning. Both the gamma- and beta- negative binomial processes are shown to significantly outperform the gamma-Poisson process for document categorization, with comparable performance to other state-of-the-art supervised text classification algorithms.
To date, there have been massive Semi-Structured Documents (SSDs) during the evolution of the Internet. These SSDs contain both unstructured features (e.g., plain text) and metadata (e.g., tags). Most previous works focused on modeling the unstructured text, and recently, some other methods have been proposed to model the unstructured text with specific tags. To build a general model for SSDs remains an important problem in terms of both model fitness and efficiency. We propose a novel method to model the SSDs by a so-called Tag-Weighted Topic Model (TWTM). TWTM is a framework that leverages both the tags and words information, not only to learn the document-topic and topic-word distributions, but also to infer the tag-topic distributions for text mining tasks. We present an efficient variational inference method with an EM algorithm for estimating the model parameters. Meanwhile, we propose three large-scale solutions for our model under the MapReduce distributed computing platform for modeling large-scale SSDs. The experimental results show the effectiveness, efficiency and the robustness by comparing our model with the state-of-the-art methods in document modeling, tags prediction and text classification. We also show the performance of the three distributed solutions in terms of time and accuracy on document modeling.
Based on the sense definition of words available in the Bengali WordNet, an attempt is made to classify the Bengali sentences automatically into different groups in accordance with their underlying senses. The input sentences are collected from 50 different categories of the Bengali text corpus developed in the TDIL project of the Govt. of India, while information about the different senses of particular ambiguous lexical item is collected from Bengali WordNet. In an experimental basis we have used Naive Bayes probabilistic model as a useful classifier of sentences. We have applied the algorithm over 1747 sentences that contain a particular Bengali lexical item which, because of its ambiguous nature, is able to trigger different senses that render sentences in different meanings. In our experiment we have achieved around 84% accurate result on the sense classification over the total input sentences. We have analyzed those residual sentences that did not comply with our experiment and did affect the results to note that in many cases, wrong syntactic structures and less semantic information are the main hurdles in semantic classification of sentences. The applicational relevance of this study is attested in automatic text classification, machine learning, information extraction, and word sense disambiguation.
Distributed word representations are very useful for capturing semantic information and have been successfully applied in a variety of NLP tasks, especially on English. In this work, we innovatively develop two component-enhanced Chinese character embedding models and their bigram extensions. Distinguished from English word embeddings, our models explore the compositions of Chinese characters, which often serve as semantic indictors inherently. The evaluations on both word similarity and text classification demonstrate the effectiveness of our models.
Text classification is a widely studied problem, and it can be considered solved for some domains and under certain circumstances. There are scenarios, however, that have received little or no attention at all, despite its relevance and applicability. One of such scenarios is early text classification, where one needs to know the category of a document by using partial information only. A document is processed as a sequence of terms, and the goal is to devise a method that can make predictions as fast as possible. The importance of this variant of the text classification problem is evident in domains like sexual predator detection, where one wants to identify an offender as early as possible. This paper analyzes the suitability of the standard naive Bayes classifier for approaching this problem. Specifically, we assess its performance when classifying documents after seeing an increasingly number of terms. A simple modification to the standard naive Bayes implementation allows us to make predictions with partial information. To the best of our knowledge naive Bayes has not been used for this purpose before. Throughout an extensive experimental evaluation we show the effectiveness of the classifier for early text classification. What is more, we show that this simple solution is very competitive when compared with state of the art methodologies that are more elaborated. We foresee our work will pave the way for the development of more effective early text classification techniques based in the naive Bayes formulation.
We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing. The second approach is to use a sequence autoencoder, which reads the input sequence into a vector and predicts the input sequence again. These two algorithms can be used as a "pretraining" step for a later supervised sequence learning algorithm. In other words, the parameters obtained from the unsupervised step can be used as a starting point for other supervised training models. In our experiments, we find that long short term memory recurrent networks after being pretrained with the two approaches are more stable and generalize better. With pretraining, we are able to train long short term memory recurrent networks up to a few hundred timesteps, thereby achieving strong performance in many text classification tasks, such as IMDB, DBpedia and 20 Newsgroups.
This paper presents a new semi-supervised framework with convolutional neural networks (CNNs) for text categorization. Unlike the previous approaches that rely on word embeddings, our method learns embeddings of small text regions from unlabeled data for integration into a supervised CNN. The proposed scheme for embedding learning is based on the idea of two-view semi-supervised learning, which is intended to be useful for the task of interest even though the training is done on unlabeled data. Our models achieve better results than previous approaches on sentiment classification and topic classification tasks.
We describe the problem of aggregating the label predictions of diverse classifiers using a class taxonomy. Such a taxonomy may not have been available or referenced when the individual classifiers were designed and trained, yet mapping the output labels into the taxonomy is desirable to integrate the effort spent in training the constituent classifiers. A hierarchical taxonomy representing some domain knowledge may be different from, but partially mappable to, the label sets of the individual classifiers. We present a heuristic approach and a principled graphical model to aggregate the label predictions by grounding them into the available taxonomy. Our model aggregates the labels using the taxonomy structure as constraints to find the most likely hierarchically consistent class. We experimentally validate our proposed method on image and text classification tasks.
Neural network models have been demonstrated to be capable of achieving remarkable performance in sentence and document modeling. Convolutional neural network (CNN) and recurrent neural network (RNN) are two mainstream architectures for such modeling tasks, which adopt totally different ways of understanding natural languages. In this work, we combine the strengths of both architectures and propose a novel and unified model called C-LSTM for sentence representation and text classification. C-LSTM utilizes CNN to extract a sequence of higher-level phrase representations, and are fed into a long short-term memory recurrent neural network (LSTM) to obtain the sentence representation. C-LSTM is able to capture both local features of phrases as well as global and temporal sentence semantics. We evaluate the proposed architecture on sentiment classification and question classification tasks. The experimental results show that the C-LSTM outperforms both CNN and LSTM and can achieve excellent performance on these tasks.
Distributed word representations have been demonstrated to be effective in capturing semantic and syntactic regularities. Unsupervised representation learning from large unlabeled corpora can learn similar representations for those words that present similar co-occurrence statistics. Besides local occurrence statistics, global topical information is also important knowledge that may help discriminate a word from another. In this paper, we incorporate category information of documents in the learning of word representations and to learn the proposed models in a document-wise manner. Our models outperform several state-of-the-art models in word analogy and word similarity tasks. Moreover, we evaluate the learned word vectors on sentiment analysis and text classification tasks, which shows the superiority of our learned word vectors. We also learn high-quality category embeddings that reflect topical meanings.
In recent years, multi-label classification has attracted a significant body of research, motivated by real-life applications, such as text classification and medical diagnoses. Although sparsely studied in this context, Learning Classifier Systems are naturally well-suited to multi-label classification problems, whose search space typically involves multiple highly specific niches. This is the motivation behind our current work that introduces a generalized multi-label rule format -- allowing for flexible label-dependency modeling, with no need for explicit knowledge of which correlations to search for -- and uses it as a guide for further adapting the general Michigan-style supervised Learning Classifier System framework. The integration of the aforementioned rule format and framework adaptations results in a novel algorithm for multi-label classification whose behavior is studied through a set of properly defined artificial problems. The proposed algorithm is also thoroughly evaluated on a set of multi-label datasets and found competitive to other state-of-the-art multi-label classification methods.
A Support Vector Machine (SVM) has become a very popular machine learning method for text classification. One reason for this relates to the range of existing kernels which allow for classifying data that is not linearly separable. The linear, polynomial and RBF (Gaussian Radial Basis Function) kernel are commonly used and serve as a basis of comparison in our study. We show how to derive the primal form of the quadratic Power Kernel (PK) -- also called the Negative Euclidean Distance Kernel (NDK) -- by means of complex numbers. We exemplify the NDK in the framework of text categorization using the Dewey Document Classification (DDC) as the target scheme. Our evaluation shows that the power kernel produces F-scores that are comparable to the reference kernels, but is -- except for the linear kernel -- faster to compute. Finally, we show how to extend the NDK-approach by including the Mahalanobis distance.
We introduce Trans-gram, a simple and computationally-efficient method to simultaneously learn and align wordembeddings for a variety of languages, using only monolingual data and a smaller set of sentence-aligned data. We use our new method to compute aligned wordembeddings for twenty-one languages using English as a pivot language. We show that some linguistic features are aligned across languages for which we do not have aligned data, even though those properties do not exist in the pivot language. We also achieve state of the art results on standard cross-lingual text classification and word translation tasks.
Automated feature selection is important for text categorization to reduce the feature size and to speed up the learning process of classifiers. In this paper, we present a novel and efficient feature selection framework based on the Information Theory, which aims to rank the features with their discriminative capacity for classification. We first revisit two information measures: Kullback-Leibler divergence and Jeffreys divergence for binary hypothesis testing, and analyze their asymptotic properties relating to type I and type II errors of a Bayesian classifier. We then introduce a new divergence measure, called Jeffreys-Multi-Hypothesis (JMH) divergence, to measure multi-distribution divergence for multi-class classification. Based on the JMH-divergence, we develop two efficient feature selection methods, termed maximum discrimination ($MD$) and $MD-\chi^2$ methods, for text categorization. The promising results of extensive experiments demonstrate the effectiveness of the proposed approaches.
The information age has brought a deluge of data. Much of this is in text form, insurmountable in scope for humans and incomprehensible in structure for computers. Text mining is an expanding field of research that seeks to utilize the information contained in vast document collections. General data mining methods based on machine learning face challenges with the scale of text data, posing a need for scalable text mining methods. This thesis proposes a solution to scalable text mining: generative models combined with sparse computation. A unifying formalization for generative text models is defined, bringing together research traditions that have used formally equivalent models, but ignored parallel developments. This framework allows the use of methods developed in different processing tasks such as retrieval and classification, yielding effective solutions across different text mining tasks. Sparse computation using inverted indices is proposed for inference on probabilistic models. This reduces the computational complexity of the common text mining operations according to sparsity, yielding probabilistic models with the scalability of modern search engines. The proposed combination provides sparse generative models: a solution for text mining that is general, effective, and scalable. Extensive experimentation on text classification and ranked retrieval datasets are conducted, showing that the proposed solution matches or outperforms the leading task-specific methods in effectiveness, with a order of magnitude decrease in classification times for Wikipedia article categorization with a million classes. The developed methods were further applied in two 2014 Kaggle data mining prize competitions with over a hundred competing teams, earning first and second places.
Most tasks in natural language processing can be cast into question answering (QA) problems over language input. We introduce the dynamic memory network (DMN), a neural network architecture which processes input sequences and questions, forms episodic memories, and generates relevant answers. Questions trigger an iterative attention process which allows the model to condition its attention on the inputs and the result of previous iterations. These results are then reasoned over in a hierarchical recurrent sequence model to generate answers. The DMN can be trained end-to-end and obtains state-of-the-art results on several types of tasks and datasets: question answering (Facebook's bAbI dataset), text classification for sentiment analysis (Stanford Sentiment Treebank) and sequence modeling for part-of-speech tagging (WSJ-PTB). The training for these different tasks relies exclusively on trained word vector representations and input-question-answer triplets.
Recent approaches based on artificial neural networks (ANNs) have shown promising results for short-text classification. However, many short texts occur in sequences (e.g., sentences in a document or utterances in a dialog), and most existing ANN-based systems do not leverage the preceding short texts when classifying a subsequent one. In this work, we present a model based on recurrent neural networks and convolutional neural networks that incorporates the preceding short texts. Our model achieves state-of-the-art results on three different datasets for dialog act prediction.