We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or snippets) that support their overall document categorization, i.e., they provide rationales. Our model exploits such supervision via a hierarchical approach in which each document is represented by a linear combination of the vector representations of its component sentences. We propose a sentence-level convolutional model that estimates the probability that a given sentence is a rationale, and we then scale the contribution of each sentence to the aggregate document representation in proportion to these estimates. Experiments on five classification datasets that have document labels and associated rationales demonstrate that our approach consistently outperforms strong baselines. Moreover, our model naturally provides explanations for its predictions.
This paper proposes an architecture for deep neural networks with hidden layer branches that learn targets of lower hierarchy than final layer targets. The branches provide a channel for enforcing useful information in hidden layer which helps in attaining better accuracy, both for the final layer and hidden layers. The shared layers modify their weights using the gradients of all cost functions higher than the branching layer. This model provides a flexible inference system with many levels of targets which is modular and can be used efficiently in situations requiring different levels of results according to complexity. This paper applies the idea to a text classification task on 20 Newsgroups data set with two level of hierarchical targets and a comparison is made with training without the use of hidden layer branches.
We describe the course of a hackathon dedicated to the development of linguistic tools for Tibetan Buddhist studies. Over a period of five days, a group of seventeen scholars, scientists, and students developed and compared algorithms for intertextual alignment and text classification, along with some basic language tools, including a stemmer and word segmenter.
This paper presents a number of experiments to model changes in a historical Portuguese corpus composed of literary texts for the purpose of temporal text classification. Algorithms were trained to classify texts with respect to their publication date taking into account lexical variation represented as word n-grams, and morphosyntactic variation represented by part-of-speech (POS) distribution. We report results of 99.8% accuracy using word unigram features with a Support Vector Machines classifier to predict the publication date of documents in time intervals of both one century and half a century. A feature analysis is performed to investigate the most informative features for this task and how they are linked to language change.
Term weighting metrics assign weights to terms in order to discriminate the important terms from the less crucial ones. Due to this characteristic, these metrics have attracted growing attention in text classification and recently in sentiment analysis. Using the weights given by such metrics could lead to more accurate document representation which may improve the performance of the classification. While previous studies have focused on proposing or comparing different weighting metrics at two-classes document level sentiment analysis, this study propose to analyse the results given by each metric in order to find out the characteristics of good and bad weighting metrics. Therefore we present an empirical study of fifteen global supervised weighting metrics with four local weighting metrics adopted from information retrieval, we also give an analysis to understand the behavior of each metric by observing and analysing how each metric distributes the terms and deduce some characteristics which may distinguish the good and bad metrics. The evaluation has been done using Support Vector Machine on three different datasets: Twitter, restaurant and laptop reviews.
This article provides an interesting exploration of character-level convolutional neural network solving Chinese corpus text classification problem. We constructed a large-scale Chinese language dataset, and the result shows that character-level convolutional neural network works better on Chinese corpus than its corresponding pinyin format dataset. This is the first time that character-level convolutional neural network applied to text classification problem.
Recurrent Neural Network (RNN) is one of the most popular architectures used in Natural Language Processsing (NLP) tasks because its recurrent structure is very suitable to process variable-length text. RNN can utilize distributed representations of words by first converting the tokens comprising each text into vectors, which form a matrix. And this matrix includes two dimensions: the time-step dimension and the feature vector dimension. Then most existing models usually utilize one-dimensional (1D) max pooling operation or attention-based operation only on the time-step dimension to obtain a fixed-length vector. However, the features on the feature vector dimension are not mutually independent, and simply applying 1D pooling operation over the time-step dimension independently may destroy the structure of the feature representation. On the other hand, applying two-dimensional (2D) pooling operation over the two dimensions may sample more meaningful features for sequence modeling tasks. To integrate the features on both dimensions of the matrix, this paper explores applying 2D max pooling operation to obtain a fixed-length representation of the text. This paper also utilizes 2D convolution to sample more meaningful information of the matrix. Experiments are conducted on six text classification tasks, including sentiment analysis, question classification, subjectivity classification and newsgroup classification. Compared with the state-of-the-art models, the proposed models achieve excellent performance on 4 out of 6 tasks. Specifically, one of the proposed models achieves highest accuracy on Stanford Sentiment Treebank binary classification and fine-grained classification tasks.
Although semi-supervised variational autoencoder (SemiVAE) works in image classification task, it fails in text classification task if using vanilla LSTM as its decoder. From a perspective of reinforcement learning, it is verified that the decoder's capability to distinguish between different categorical labels is essential. Therefore, Semi-supervised Sequential Variational Autoencoder (SSVAE) is proposed, which increases the capability by feeding label into its decoder RNN at each time-step. Two specific decoder structures are investigated and both of them are verified to be effective. Besides, in order to reduce the computational complexity in training, a novel optimization method is proposed, which estimates the gradient of the unlabeled objective function by sampling, along with two variance reduction techniques. Experimental results on Large Movie Review Dataset (IMDB) and AG's News corpus show that the proposed approach significantly improves the classification accuracy compared with pure-supervised classifiers, and achieves competitive performance against previous advanced methods. State-of-the-art results can be obtained by integrating other pretraining-based methods.
Most existing word embedding approaches do not distinguish the same words in different contexts, therefore ignoring their contextual meanings. As a result, the learned embeddings of these words are usually a mixture of multiple meanings. In this paper, we acknowledge multiple identities of the same word in different contexts and learn the \textbf{identity-sensitive} word embeddings. Based on an identity-labeled text corpora, a heterogeneous network of words and word identities is constructed to model different-levels of word co-occurrences. The heterogeneous network is further embedded into a low-dimensional space through a principled network embedding approach, through which we are able to obtain the embeddings of words and the embeddings of word identities. We study three different types of word identities including topics, sentiments and categories. Experimental results on real-world data sets show that the identity-sensitive word embeddings learned by our approach indeed capture different meanings of words and outperforms competitive methods on tasks including text classification and word similarity computation.
Developed so far, multi-document summarization has reached its bottleneck due to the lack of sufficient training data and diverse categories of documents. Text classification just makes up for these deficiencies. In this paper, we propose a novel summarization system called TCSum, which leverages plentiful text classification data to improve the performance of multi-document summarization. TCSum projects documents onto distributed representations which act as a bridge between text classification and summarization. It also utilizes the classification results to produce summaries of different styles. Extensive experiments on DUC generic multi-document summarization datasets show that, TCSum can achieve the state-of-the-art performance without using any hand-crafted features and has the capability to catch the variations of summary styles with respect to different text categories.
We propose a new active learning (AL) method for text classification with convolutional neural networks (CNNs). In AL, one selects the instances to be manually labeled with the aim of maximizing model performance with minimal effort. Neural models capitalize on word embeddings as representations (features), tuning these to the task at hand. We argue that AL strategies for multi-layered neural models should focus on selecting instances that most affect the embedding space (i.e., induce discriminative word representations). This is in contrast to traditional AL approaches (e.g., entropy-based uncertainty sampling), which specify higher level objectives. We propose a simple approach for sentence classification that selects instances containing words whose embeddings are likely to be updated with the greatest magnitude, thereby rapidly learning discriminative, task-specific embeddings. We extend this approach to document classification by jointly considering: (1) the expected changes to the constituent word representations; and (2) the model's current overall uncertainty regarding the instance. The relative emphasis placed on these criteria is governed by a stochastic process that favors selecting instances likely to improve representations at the outset of learning, and then shifts toward general uncertainty sampling as AL progresses. Empirical results show that our method outperforms baseline AL approaches on both sentence and document classification tasks. We also show that, as expected, the method quickly learns discriminative word embeddings. To the best of our knowledge, this is the first work on AL addressing neural models for text classification.
We investigate what distinguishes reported dreams from other personal narratives. The continuity hypothesis, stemming from psychological dream analysis work, states that most dreams refer to a person's daily life and personal concerns, similar to other personal narratives such as diary entries. Differences between the two texts may reveal the linguistic markers of dream text, which could be the basis for new dream analysis work and for the automatic detection of dream descriptions. We used three text analytics methods: text classification, topic modeling, and text coherence analysis, and applied these methods to a balanced set of texts representing dreams, diary entries, and other personal stories. We observed that dream texts could be distinguished from other personal narratives nearly perfectly, mostly based on the presence of uncertainty markers and descriptions of scenes. Important markers for non-dream narratives are specific time expressions and conversational expressions. Dream texts also exhibit a lower discourse coherence than other personal narratives.
We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutions inspired by the hashing literature, we propose a method built upon product quantization to store word embeddings. While the original technique leads to a loss in accuracy, we adapt this method to circumvent quantization artefacts. Our experiments carried out on several benchmarks show that our approach typically requires two orders of magnitude less memory than fastText while being only slightly inferior with respect to accuracy. As a result, it outperforms the state of the art by a good margin in terms of the compromise between memory usage and accuracy.
LSTMs have become a basic building block for many deep NLP models. In recent years, many improvements and variations have been proposed for deep sequence models in general, and LSTMs in particular. We propose and analyze a series of augmentations and modifications to LSTM networks resulting in improved performance for text classification datasets. We observe compounding improvements on traditional LSTMs using Monte Carlo test-time model averaging, average pooling, and residual connections, along with four other suggested modifications. Our analysis provides a simple, reliable, and high quality baseline model.
In this paper we propose a new document classification method, bridging discrepancies (so-called semantic gap) between the training set and the application sets of textual data. We demonstrate its superiority over classical text classification approaches, including traditional classifier ensembles. The method consists in combining a document categorization technique with a single classifier or a classifier ensemble (SEMCOM algorithm - Committee with Semantic Categorizer).
In this paper, we describe a research method that generates Bangla word clusters on the basis of relating to meaning in language and contextual similarity. The importance of word clustering is in parts of speech (POS) tagging, word sense disambiguation, text classification, recommender system, spell checker, grammar checker, knowledge discover and for many others Natural Language Processing (NLP) applications. In the history of word clustering, English and some other languages have already implemented some methods on word clustering efficiently. But due to lack of the resources, word clustering in Bangla has not been still implemented efficiently. Presently, its implementation is in the beginning stage. In some research of word clustering in English based on preceding and next five words of a key word they found an efficient result. Now, we are trying to implement the tri-gram, 4-gram and 5-gram model of word clustering for Bangla to observe which one is the best among them. We have started our research with quite a large corpus of approximate 1 lakh Bangla words. We are using a machine learning technique in this research. We will generate word clusters and analyze the clusters by testing some different threshold values.
The dominant approach for many NLP tasks are recurrent neural networks, in particular LSTMs, and convolutional neural networks. However, these architectures are rather shallow in comparison to the deep convolutional networks which have pushed the state-of-the-art in computer vision. We present a new architecture (VDCNN) for text processing which operates directly at the character level and uses only small convolutions and pooling operations. We are able to show that the performance of this model increases with depth: using up to 29 convolutional layers, we report improvements over the state-of-the-art on several public text classification tasks. To the best of our knowledge, this is the first time that very deep convolutional nets have been applied to text processing.
Naive Bayes classifiers, a family of classifiers that are based on the popular Bayes' probability theorem, are known for creating simple yet well performing models, especially in the fields of document classification and disease prediction. In this article, we will look at the main concepts of naive Bayes classification in the context of document categorization.
The paper [1] shows that simple linear classifier can compete with complex deep learning algorithms in text classification applications. Combining bag of words (BoW) and linear classification techniques, fastText [1] attains same or only slightly lower accuracy than deep learning algorithms [2-9] that are orders of magnitude slower. We proved formally that fastText can be transformed into a simpler equivalent classifier, which unlike fastText does not have any hidden layer. We also proved that the necessary and sufficient dimensionality of the word vector embedding space is exactly the number of document classes. These results help constructing more optimal linear text classifiers with guaranteed maximum classification capabilities. The results are proven exactly by pure formal algebraic methods without attracting any empirical data.
We present results of empirical studies on positive speech on Twitter. By positive speech we understand speech that works for the betterment of a given situation, in this case relations between different communities in a conflict-prone country. We worked with four Twitter data sets. Through semi-manual opinion mining, we found that positive speech accounted for < 1% of the data . In fully automated studies, we tested two approaches: unsupervised statistical analysis, and supervised text classification based on distributed word representation. We discuss benefits and challenges of those approaches and report empirical evidence obtained in the study.