Despite deep recurrent neural networks (RNNs) demonstrate strong performance in text classification, training RNN models are often expensive and requires an extensive collection of annotated data which may not be available. To overcome the data limitation issue, existing approaches leverage either pre-trained word embedding or sentence representation to lift the burden of training RNNs from scratch. In this paper, we show that jointly learning sentence representations from multiple text classification tasks and combining them with pre-trained word-level and sentence level encoders result in robust sentence representations that are useful for transfer learning. Extensive experiments and analyses using a wide range of transfer and linguistic tasks endorse the effectiveness of our approach.
Open Directory Project (ODP) has been successfully utilized in text classification due to its representation ability of various categories. However, ODP includes a limited number of entities, which play an important role in classification tasks. In this paper, we enrich the semantics of ODP categories with Probase entities. To effectively incorporate Probase entities in ODP categories, we first represent each ODP category and Probase entity in terms of concepts. Next, we measure the semantic relevance between an ODP category and a Probase entity based on the concept vector. Finally, we use Probase entity to enrich the semantics of the ODP categories. Our experimental results show that the proposed methodology exhibits a significant improvement over state-of-the-art techniques in the ODP-based text classification.
In scenarios involving text classification where the number of classes is large (in multiples of 10000s) and training samples for each class are few and often verbose, nearest neighbor methods are effective but very slow in computing a similarity score with training samples of every class. On the other hand, machine learning models are fast at runtime but training them adequately is not feasible using few available training samples per class. In this paper, we propose a hybrid approach that cascades 1) a fast but less-accurate recurrent neural network (RNN) model and 2) a slow but more-accurate nearest-neighbor model using bag of syntactic features. Using the cascaded approach, our experiments, performed on data set from IT support services where customer complaint text needs to be classified to return top-$N$ possible error codes, show that the query-time of the slow system is reduced to $1/6^{th}$ while its accuracy is being improved. Our approach outperforms an LSH-based baseline for query-time reduction. We also derive a lower bound on the accuracy of the cascaded model in terms of the accuracies of the individual models. In any two-stage approach, choosing the right number of candidates to pass on to the second stage is crucial. We prove a result that aids in choosing this cutoff number for the cascaded system.
The absence of an appropriate text classification corpus makes the massive amount of online job information unusable for labor market analysis. This paper presents JCTC, a large job posting corpus for text classification. In JCTC construction framework, a formal specification issued by the Chinese central government is chosen as the classification standard. The unsupervised learning (WE-cos), supervised learning algorithm (SVM) and human judgements are all used in the construction process. JCTC has 102581 online job postings distributed in 465 categories. The method proposed here can not only ameliorate the high demands on people's skill and knowledge, but reduce the subjective influences as well. Besides, the method is not limited in Chinese. We benchmark five state-of-the-art deep learning approaches on JCTC providing baseline results for future studies. JCTC might be the first job posting corpus for text classification and the largest one in Chinese. With the help of JCTC, related organizations are able to monitor, analyze and predict the labor market in a comprehensive, accurate and timely manner.
While many methods purport to explain predictions by highlighting salient features, what aims these explanations serve and how they ought to be evaluated often go unstated. In this work, we introduce a framework to quantify the value of explanations via the accuracy gains that they confer on a student model trained to simulate a teacher model. Crucially, the explanations are available to the student during training, but are not available at test time. Compared to prior proposals, our approach is less easily gamed, enabling principled, automatic, model-agnostic evaluation of attributions. Using our framework, we compare numerous attribution methods for text classification and question answering, and observe quantitative differences that are consistent (to a moderate to high degree) across different student model architectures and learning strategies.
The COVID-19 has brought about a significant challenge to the whole of humanity, but with a special burden upon the medical community. Clinicians must keep updated continuously about symptoms, diagnoses, and effectiveness of emergent treatments under a never-ending flood of scientific literature. In this context, the role of evidence-based medicine (EBM) for curating the most substantial evidence to support public health and clinical practice turns essential but is being challenged as never before due to the high volume of research articles published and pre-prints posted daily. Artificial Intelligence can have a crucial role in this situation. In this article, we report the results of an applied research project to classify scientific articles to support Epistemonikos, one of the most active foundations worldwide conducting EBM. We test several methods, and the best one, based on the XLNet neural language model, improves the current approach by 93\% on average F1-score, saving valuable time from physicians who volunteer to curate COVID-19 research articles manually.
Supervised text classification is a classical and active area of ML research. In large enterprise, solutions to this problem has significant importance. This is specifically true in ticketing systems where prediction of the type and subtype of tickets given new incoming ticket text to find out optimal routing is a multi billion dollar industry. In this paper authors describe a class of industrial standard algorithms which can accurately ( 86\% and above ) predict classification of any text given prior labelled text data - by novel use of any text search engine. These algorithms were used to automate routing of issue tickets to the appropriate team. This class of algorithms has far reaching consequences for a wide variety of industrial applications, IT support, RPA script triggering, even legal domain where massive set of pre labelled data are already available.
Distributional text clustering delivers semantically informative representations and captures the relevance between each word and semantic clustering centroids. We extend the neural text clustering approach to text classification tasks by inducing cluster centers via a latent variable model and interacting with distributional word embeddings, to enrich the representation of tokens and measure the relatedness between tokens and each learnable cluster centroid. The proposed method jointly learns word clustering centroids and clustering-token alignments, achieving the state of the art results on multiple benchmark datasets and proving that the proposed cluster-token alignment mechanism is indeed favorable to text classification. Notably, our qualitative analysis has conspicuously illustrated that text representations learned by the proposed model are in accord well with our intuition.
Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes. In real-world datasets, however, the number of instances vary substantially among classes. This typically leads to a learner that promotes bias towards the majority group due to its dominating property. Therefore, methods to handle imbalanced datasets are crucial for alleviating distributional skews and fully utilizing the under-represented data, especially in text classification. While addressing the imbalance in text data, most methods utilize sampling methods on the numerical representation of the data, which limits its efficiency on how effective the representation is. We propose a novel training method, Sequential Targeting(ST), independent of the effectiveness of the representation method, which enforces an incremental learning setting by splitting the data into mutually exclusive subsets and training the learner adaptively. To address problems that arise within incremental learning, we apply elastic weight consolidation. We demonstrate the effectiveness of our method through experiments on simulated benchmark datasets (IMDB) and data collected from NAVER.
The attention mechanism has been widely used in deep neural networks as a model component. By now, it has become a critical building block in many state-of-the-art natural language models. Despite its great success established empirically, the working mechanism of attention has not been investigated at a sufficient theoretical depth to date. In this paper, we set up a simple text classification task and study the dynamics of training a simple attention-based classification model using gradient descent. In this setting, we show that, for the discriminative words that the model should attend to, a persisting identity exists relating its embedding and the inner product of its key and the query. This allows us to prove that training must converge to attending to the discriminative words when the attention output is classified by a linear classifier. Experiments are performed, which validate our theoretical analysis and provide further insights.
In this paper, we propose a rule-based engine composed of high quality and interpretable regular expressions for medical text classification. The regular expressions are auto generated by a constructive heuristic method and optimized using a Pool-based Simulated Annealing (PSA) approach. Although existing Deep Neural Network (DNN) methods present high quality performance in most Natural Language Processing (NLP) applications, the solutions are regarded as uninterpretable black boxes to humans. Therefore, rule-based methods are often introduced when interpretable solutions are needed, especially in the medical field. However, the construction of regular expressions can be extremely labor-intensive for large data sets. This research aims to reduce the manual efforts while maintaining high-quality solutions
Most supervised text classification approaches assume a closed world, counting on all classes being present in the data at training time. This assumption can lead to unpredictable behaviour during operation, whenever novel, previously unseen, classes appear. Although deep learning-based methods have recently been used for novelty detection, they are challenging to interpret due to their black-box nature. This paper addresses \emph{interpretable} open-world text classification, where the trained classifier must deal with novel classes during operation. To this end, we extend the recently introduced Tsetlin machine (TM) with a novelty scoring mechanism. The mechanism uses the conjunctive clauses of the TM to measure to what degree a text matches the classes covered by the training data. We demonstrate that the clauses provide a succinct interpretable description of known topics, and that our scoring mechanism makes it possible to discern novel topics from the known ones. Empirically, our TM-based approach outperforms seven other novelty detection schemes on three out of five datasets, and performs second and third best on the remaining, with the added benefit of an interpretable propositional logic-based representation.
The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make the best use of U is poorly understood: is semi-supervised learning still beneficial with the presence of large-scale pretraining? should U be used for in-domain LM pretraining or pseudo-label generation? how should the pseudo-label based semi-supervised model be actually implemented? how different semi-supervised strategies affect performances regarding D of different sizes, U of different sizes, etc. In this paper, we conduct comprehensive studies on semi-supervised learning in the task of text classification under the context of large-scale LM pretraining. Our studies shed important lights on the behavior of semi-supervised learning methods: (1) with the presence of in-domain pretraining LM on U, open-domain LM pretraining is unnecessary; (2) both the in-domain pretraining strategy and the pseudo-label based strategy introduce significant performance boosts, with the former performing better with larger U, the latter performing better with smaller U, and the combination leading to the largest performance boost; (3) self-training (pretraining first on pseudo labels D' and then fine-tuning on D) yields better performances when D is small, while joint training on the combination of pseudo labels D' and the original dataset D yields better performances when D is large. Using semi-supervised learning strategies, we are able to achieve a performance of around 93.8% accuracy with only 50 training data points on the IMDB dataset, and a competitive performance of 96.6% with the full IMDB dataset. Our work marks an initial step in understanding the behavior of semi-supervised learning models under the context of large-scale pretraining.
Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we present the first study to systematically investigate the transferability of adversarial examples for text classification models and explore how various factors, including network architecture, tokenization scheme, word embedding, and model capacity, affect the transferability of adversarial examples. Based on these studies, we propose a genetic algorithm to find an ensemble of models that can be used to induce adversarial examples to fool almost all existing models. Such adversarial examples reflect the defects of the learning process and the data bias in the training set. Finally, we derive word replacement rules that can be used for model diagnostics from these adversarial examples.
Recently, the use of pre-trained model to build neural network based on transfer learning methodology is increasingly popular. These pre-trained models present the benefit of using less computing resources to train model with smaller amount of training data. The rise of state-of-the-art models such as BERT, XLNet and GPT boost accuracy and benefit as a base model for transfer leanring. However, these models are still too complex and consume many computing resource to train for transfer learning with low GPU memory. We will compare the performance and cost between lighter transfer learning model and purposely built neural network for NLP application of text classification and NER model.
At present, the review process for material that is exempt from disclosure under the Freedom of Information Act (FOIA) in the United States of America, and under many similar government transparency regimes worldwide, is entirely manual. Public access to the records of their government is thus inhibited by the long backlogs of material awaiting such reviews. This paper studies one aspect of that problem by first creating a new public test collection with annotations for one class of exempt material, the deliberative process privilege, and then by using that test collection to study the ability of current text classification techniques to identify those materials that are exempt from release under that privilege. Results show that when the system is trained and evaluated using annotations from the same reviewer that even difficult cases can often be reliably detected, but that differences in reviewer interpretations, differences in record custodians, and that differences in topics of the records used for training and testing pose additional challenges.
A lot of natural language processing problems need to encode the text sequence as a fix-length vector, which usually involves aggregation process of combining the representations of all the words, such as pooling or self-attention. However, these widely used aggregation approaches did not take higher-order relationship among the words into consideration. Hence we propose a new way of obtaining aggregation weights, called eigen-centrality self-attention. More specifically, we build a fully-connected graph for all the words in a sentence, then compute the eigen-centrality as the attention score of each word. The explicit modeling of relationships as a graph is able to capture some higher-order dependency among words, which helps us achieve better results in 5 text classification tasks and one SNLI task than baseline models such as pooling, self-attention and dynamic routing. Besides, in order to compute the dominant eigenvector of the graph, we adopt power method algorithm to get the eigen-centrality measure. Moreover, we also derive an iterative approach to get the gradient for the power method process to reduce both memory consumption and computation requirement.}
This paper presents the 'hyper-sinh', a variation of the m-arcsinh activation function suitable for Deep Learning (DL)-based algorithms for supervised learning, such as Convolutional Neural Networks (CNN). hyper-sinh, developed in the open source Python libraries TensorFlow and Keras, is thus described and validated as an accurate and reliable activation function for both shallow and deep neural networks. Improvements in accuracy and reliability in image and text classification tasks on five (N = 5) benchmark data sets available from Keras are discussed. Experimental results demonstrate the overall competitive classification performance of both shallow and deep neural networks, obtained via this novel function. This function is evaluated with respect to gold standard activation functions, demonstrating its overall competitive accuracy and reliability for both image and text classification.
Unstructured clinical text in EHRs contains crucial information for applications including decision support, trial matching, and retrospective research. Recent work has applied BERT-based models to clinical information extraction and text classification, given these models' state-of-the-art performance in other NLP domains. However, BERT is difficult to apply to clinical notes because it doesn't scale well to long sequences of text. In this work, we propose a novel fine-tuning approach called SnipBERT. Instead of using entire notes, SnipBERT identifies crucial snippets and then feeds them into a truncated BERT-based model in a hierarchical manner. Empirically, SnipBERT not only has significant predictive performance gain across three tasks but also provides improved interpretability, as the model can identify key pieces of text that led to its prediction.
Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes. It can be applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning. Moreover, we also investigate the application of these methods in reinforcement learning (RL). Then, we outline a few important applications of UQ methods. Finally, we briefly highlight the fundamental research challenges faced by UQ methods and discuss the future research directions in this field.