Sentiment classification is a fundamental task in content analysis. Although deep learning has demonstrated promising performance in text classification compared with shallow models, it is still not able to train a satisfying classifier for text sentiment. Human beings are more sophisticated than machine learning models in terms of understanding and capturing the emotional polarities of texts. In this paper, we leverage the power of human intelligence into text sentiment classification. We propose Crowd-based neural networks for Text Sentiment Classification (CrowdTSC for short). We design and post the questions on a crowdsourcing platform to collect the keywords in texts. Sampling and clustering are utilized to reduce the cost of crowdsourcing. Also, we present an attention-based neural network and a hybrid neural network, which incorporate the collected keywords as human being's guidance into deep neural networks. Extensive experiments on public datasets confirm that CrowdTSC outperforms state-of-the-art models, justifying the effectiveness of crowd-based keyword guidance.
This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amount of augmented training samples by interpolating text in hidden space. Moreover, we leverage recent advances in data augmentation to guess low-entropy labels for unlabeled data, hence making them as easy to use as labeled data.By mixing labeled, unlabeled and augmented data, MixText significantly outperformed current pre-trained and fined-tuned models and other state-of-the-art semi-supervised learning methods on several text classification benchmarks. The improvement is especially prominent when supervision is extremely limited. We have publicly released our code at https://github.com/GT-SALT/MixText.
Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks. However, when paired with strong autoregressive decoders, VAE often converges to a degenerated local optimum known as "posterior collapse". Previous approaches consider the Kullback Leibler divergence (KL) individual for each datapoint. We propose to let the KL follow a distribution across the whole dataset, and analyze that it is sufficient to prevent posterior collapse by keeping the expectation of the KL's distribution positive. Then we propose Batch Normalized-VAE (BN-VAE), a simple but effective approach to set a lower bound of the expectation by regularizing the distribution of the approximate posterior's parameters. Without introducing any new model component or modifying the objective, our approach can avoid the posterior collapse effectively and efficiently. We further show that the proposed BN-VAE can be extended to conditional VAE (CVAE). Empirically, our approach surpasses strong autoregressive baselines on language modeling, text classification and dialogue generation, and rivals more complex approaches while keeping almost the same training time as VAE.
Fine-tuning of pre-trained transformer networks such as BERT yield state-of-the-art results for text classification tasks. Typically, fine-tuning is performed on task-specific training datasets in a supervised manner. One can also fine-tune in unsupervised manner beforehand by further pre-training the masked language modeling (MLM) task. Hereby, in-domain data for unsupervised MLM resembling the actual classification target dataset allows for domain adaptation of the model. In this paper, we compare current pre-trained transformer networks with and without MLM fine-tuning on their performance for offensive language detection. Our MLM fine-tuned RoBERTa-based classifier officially ranks 1st in the SemEval 2020 Shared Task~12 for the English language. Further experiments with the ALBERT model even surpass this result.
Most topic models are constructed under the assumption that documents follow a multinomial distribution. The Poisson distribution is an alternative distribution to describe the probability of count data. For topic modelling, the Poisson distribution describes the number of occurrences of a word in documents of fixed length. The Poisson distribution has been successfully applied in text classification, but its application to topic modelling is not well documented, specifically in the context of a generative probabilistic model. Furthermore, the few Poisson topic models in literature are admixture models, making the assumption that a document is generated from a mixture of topics. In this study, we focus on short text. Many studies have shown that the simpler assumption of a mixture model fits short text better. With mixture models, as opposed to admixture models, the generative assumption is that a document is generated from a single topic. One topic model, which makes this one-topic-per-document assumption, is the Dirichlet-multinomial mixture model. The main contributions of this work are a new Gamma-Poisson mixture model, as well as a collapsed Gibbs sampler for the model. The benefit of the collapsed Gibbs sampler derivation is that the model is able to automatically select the number of topics contained in the corpus. The results show that the Gamma-Poisson mixture model performs better than the Dirichlet-multinomial mixture model at selecting the number of topics in labelled corpora. Furthermore, the Gamma-Poisson mixture produces better topic coherence scores than the Dirichlet-multinomial mixture model, thus making it a viable option for the challenging task of topic modelling of short text.
We present semi-supervised models with data augmentation (SMDA), a semi-supervised text classification system to classify interactive affective responses. SMDA utilizes recent transformer-based models to encode each sentence and employs back translation techniques to paraphrase given sentences as augmented data. For labeled sentences, we performed data augmentations to uniform the label distributions and computed supervised loss during training process. For unlabeled sentences, we explored self-training by regarding low-entropy predictions over unlabeled sentences as pseudo labels, assuming high-confidence predictions as labeled data for training. We further introduced consistency regularization as unsupervised loss after data augmentations on unlabeled data, based on the assumption that the model should predict similar class distributions with original unlabeled sentences as input and augmented sentences as input. Via a set of experiments, we demonstrated that our system outperformed baseline models in terms of F1-score and accuracy.
We present ktrain, a low-code Python library that makes machine learning more accessible and easier to apply. As a wrapper to TensorFlow and many other libraries (e.g., transformers, scikit-learn, stellargraph), it is designed to make sophisticated, state-of-the-art machine learning models simple to build, train, inspect, and apply by both beginners and experienced practitioners. Featuring modules that support text data (e.g., text classification, sequence tagging, open-domain question-answering), vision data (e.g., image classification), graph data (e.g., node classification, link prediction), and tabular data, ktrain presents a simple unified interface enabling one to quickly solve a wide range of tasks in as little as three or four "commands" or lines of code.
Mining social media content for tasks such as detecting personal experiences or events, suffer from lexical sparsity, insufficient training data, and inventive lexicons. To reduce the burden of creating extensive labeled data and improve classification performance, we propose to perform these tasks in two steps: 1. Decomposing the task into domain-specific sub-tasks by identifying key concepts, thus utilizing human domain understanding; and 2. Combining the results of learners for each key concept using co-training to reduce the requirements for labeled training data. We empirically show the effectiveness and generality of our approach, Co-Decomp, using three representative social media mining tasks, namely Personal Health Mention detection, Crisis Report detection, and Adverse Drug Reaction monitoring. The experiments show that our model is able to outperform the state-of-the-art text classification models--including those using the recently introduced BERT model--when small amounts of training data are available.
Off-topic spoken response detection, the task aiming at predicting whether a response is off-topic for the corresponding prompt, is important for an automated speaking assessment system. In many real-world educational applications, off-topic spoken response detectors are required to achieve high recall for off-topic responses not only on seen prompts but also on prompts that are unseen during training. In this paper, we propose a novel approach for off-topic spoken response detection with high off-topic recall on both seen and unseen prompts. We introduce a new model, Gated Convolutional Bidirectional Attention-based Model (GCBiA), which applies bi-attention mechanism and convolutions to extract topic words of prompts and key-phrases of responses, and introduces gated unit and residual connections between major layers to better represent the relevance of responses and prompts. Moreover, a new negative sampling method is proposed to augment training data. Experiment results demonstrate that our novel approach can achieve significant improvements in detecting off-topic responses with extremely high on-topic recall, for both seen and unseen prompts.
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.
As NLP models become larger, executing a trained model requires significant computational resources incurring monetary and environmental costs. To better respect a given inference budget, we propose a modification to contextual representation fine-tuning which, during inference, allows for an early (and fast) "exit" from neural network calculations for simple instances, and late (and accurate) exit for hard instances. To achieve this, we add classifiers to different layers of BERT and use their calibrated confidence scores to make early exit decisions. We test our proposed modification on five different datasets in two tasks: three text classification datasets and two natural language inference benchmarks. Our method presents a favorable speed/accuracy tradeoff in almost all cases, producing models which are up to five times faster than the state of the art, while preserving their accuracy. Our method also requires almost no additional training resources (in either time or parameters) compared to the baseline BERT model. Finally, our method alleviates the need for costly retraining of multiple models at different levels of efficiency; we allow users to control the inference speed/accuracy tradeoff using a single trained model, by setting a single variable at inference time. We publicly release our code.
Social determinants of health (SDOH) affect health outcomes, and knowledge of SDOH can inform clinical decision-making. Automatically extracting SDOH information from clinical text requires data-driven information extraction models trained on annotated corpora that are heterogeneous and frequently include critical SDOH. This work presents a new corpus with SDOH annotations, a novel active learning framework, and the first extraction results on the new corpus. The Social History Annotation Corpus (SHAC) includes 4,480 social history sections with detailed annotation for 12 SDOH characterizing the status, extent, and temporal information of 18K distinct events. We introduce a novel active learning framework that selects samples for annotation using a surrogate text classification task as a proxy for a more complex event extraction task. The active learning framework successfully increases the frequency of health risk factors and improves automatic extraction of these events over undirected annotation. An event extraction model trained on SHAC achieves high extraction performance for substance use status (0.82-0.93 F1), employment status (0.81-0.86 F1), and living status type (0.81-0.93 F1) on data from three institutions.
Recent efforts have shown that neural text processing models are vulnerable to adversarial examples, but the nature of these examples is poorly understood. In this work, we show that adversarial attacks against CNN, LSTM and Transformer-based classification models perform word substitutions that are identifiable through frequency differences between replaced words and their corresponding substitutions. Based on these findings, we propose frequency-guided word substitutions (FGWS), a simple algorithm exploiting the frequency properties of adversarial word substitutions for the detection of adversarial examples. FGWS achieves strong performance by accurately detecting adversarial examples on the SST-2 and IMDb sentiment datasets, with F1 detection scores of up to 91.4% against RoBERTa-based classification models. We compare our approach against a recently proposed perturbation discrimination framework and show that we outperform it by up to 13.0% F1.
At the heart of text based neural models lay word representations, which are powerful but occupy a lot of memory making it challenging to deploy to devices with memory constraints such as mobile phones, watches and IoT. To surmount these challenges, we introduce ProFormer -- a projection based transformer architecture that is faster and lighter making it suitable to deploy to memory constraint devices and preserve user privacy. We use LSH projection layer to dynamically generate word representations on-the-fly without embedding lookup tables leading to significant memory footprint reduction from O(V.d) to O(T), where V is the vocabulary size, d is the embedding dimension size and T is the dimension of the LSH projection representation. We also propose a local projection attention (LPA) layer, which uses self-attention to transform the input sequence of N LSH word projections into a sequence of N/K representations reducing the computations quadratically by O(K^2). We evaluate ProFormer on multiple text classification tasks and observed improvements over prior state-of-the-art on-device approaches for short text classification and comparable performance for long text classification tasks. In comparison with a 2-layer BERT model, ProFormer reduced the embedding memory footprint from 92.16 MB to 1.3 KB and requires 16 times less computation overhead, which is very impressive making it the fastest and smallest on-device model.
Much progress has been made recently on text classification with methods based on neural networks. In particular, models using attention mechanism such as BERT have shown to have the capability of capturing the contextual information within a sentence or document. However, their ability of capturing the global information about the vocabulary of a language is more limited. This latter is the strength of Graph Convolutional Networks (GCN). In this paper, we propose VGCN-BERT model which combines the capability of BERT with a Vocabulary Graph Convolutional Network (VGCN). Local information and global information interact through different layers of BERT, allowing them to influence mutually and to build together a final representation for classification. In our experiments on several text classification datasets, our approach outperforms BERT and GCN alone, and achieve higher effectiveness than that reported in previous studies.
Invariant risk minimization (IRM) (Arjovsky et al., 2019) is a recently proposed framework designed for learning predictors that are invariant to spurious correlations across different training environments. Yet, despite its theoretical justifications, IRM has not been extensively tested across various settings. In an attempt to gain a better understanding of the framework, we empirically investigate several research questions using IRMv1, which is the first practical algorithm proposed to approximately solve IRM. By extending the ColoredMNIST experiment in different ways, we find that IRMv1 (i) performs better as the spurious correlation varies more widely between training environments, (ii) learns an approximately invariant predictor when the underlying relationship is approximately invariant, and (iii) can be extended to an analogous setting for text classification.
Fine-tuning (FT) pre-trained sentence embedding models on small datasets has been shown to have limitations. In this paper we show that concatenating the embeddings from the pre-trained model with those from a simple sentence embedding model trained only on the target data, can improve over the performance of FT for few-sample tasks. To this end, a linear classifier is trained on the combined embeddings, either by freezing the embedding model weights or training the classifier and embedding models end-to-end. We perform evaluation on seven small datasets from NLP tasks and show that our approach with end-to-end training outperforms FT with negligible computational overhead. Further, we also show that sophisticated combination techniques like CCA and KCCA do not work as well in practice as concatenation. We provide theoretical analysis to explain this empirical observation.
Deep learning based models have surpassed classical machine learning based approaches in various text classification tasks, including sentiment analysis, news categorization, question answering, and natural language inference. In this paper, we provide a comprehensive review of more than 150 deep learning based models for text classification developed in recent years, and discuss their technical contributions, similarities, and strengths. We also provide a summary of more than 40 popular datasets widely used for text classification. Finally, we provide a quantitative analysis of the performance of different deep learning models on popular benchmarks, and discuss future research directions.
The main goal of this research is to produce a useful software for United Nations (UN), that could help to speed up the process of qualifying the UN documents following the Sustainable Development Goals (SDGs) in order to monitor the progresses at the world level to fight poverty, discrimination, climate changes. In fact human labeling of UN documents would be a daunting task given the size of the impacted corpus. Thus, automatic labeling must be adopted at least as a first step of a multi-phase process to reduce the overall effort of cataloguing and classifying. Deep Learning (DL) is nowadays one of the most powerful tools for state-of-the-art (SOTA) AI for this task, but very often it comes with the cost of an expensive and error-prone preparation of a training-set. In the case of multi-label text classification of domain-specific text it seems that we cannot effectively adopt DL without a big-enough domain-specific training-set. In this paper, we show that this is not always true. In fact we propose a novel method that is able, through statistics like TF-IDF, to exploit pre-trained SOTA DL models (such as the Universal Sentence Encoder) without any need for traditional transfer learning or any other expensive training procedure. We show the effectiveness of our method in a legal context, by classifying UN Resolutions according to their most related SDGs.
A lot of effort is currently made to provide methods to analyze and understand deep neural network impressive performances for tasks such as image or text classification. These methods are mainly based on visualizing the important input features taken into account by the network to build a decision. However these techniques, let us cite LIME, SHAP, Grad-CAM, or TDS, require extra effort to interpret the visualization with respect to expert knowledge. In this paper, we propose a novel approach to inspect the hidden layers of a fitted CNN in order to extract interpretable linguistic objects from texts exploiting classification process. In particular, we detail a weighted extension of the Text Deconvolution Saliency (wTDS) measure which can be used to highlight the relevant features used by the CNN to perform the classification task. We empirically demonstrate the efficiency of our approach on corpora from two different languages: English and French. On all datasets, wTDS automatically encodes complex linguistic objects based on co-occurrences and possibly on grammatical and syntax analysis.