Graph convolutional network (GCN) has been successfully applied to capture global non-consecutive and long-distance semantic information for text classification. However, while GCN-based methods have shown promising results in offline evaluations, they commonly follow a seen-token-seen-document paradigm by constructing a fixed document-token graph and cannot make inferences on new documents. It is a challenge to deploy them in online systems to infer steaming text data. In this work, we present a continual GCN model (ContGCN) to generalize inferences from observed documents to unobserved documents. Concretely, we propose a new all-token-any-document paradigm to dynamically update the document-token graph in every batch during both the training and testing phases of an online system. Moreover, we design an occurrence memory module and a self-supervised contrastive learning objective to update ContGCN in a label-free manner. A 3-month A/B test on Huawei public opinion analysis system shows ContGCN achieves 8.86% performance gain compared with state-of-the-art methods. Offline experiments on five public datasets also show ContGCN can improve inference quality. The source code will be released at https://github.com/Jyonn/ContGCN.

We introduce a novel kernel for comparing two text documents. The kernel is an inner product in the feature space consisting of all subsequences of length k. A subsequence is any ordered se(cid:173) quence of k characters occurring in the text though not necessarily contiguously. The subsequences are weighted by an exponentially decaying factor of their full length in the text, hence emphasising those occurrences which are close to contiguous. A direct compu(cid:173) tation of this feature vector would involve a prohibitive amount of computation even for modest values of k, since the dimension of the feature space grows exponentially with k.

Chuong B. Do, Andrew Y. Ng Linear text classification algorithms work by computing an inner prod- uct between a test document vector and a parameter vector. In many such algorithms, including naive Bayes and most TFIDF variants, the parame- ters are determined by some simple, closed-form, function of training set statistics; we call this mapping mapping from statistics to parameters, the parameter function. Much research in text classification over the last few decades has consisted of manual efforts to identify better parameter func- tions. In this paper, we propose an algorithm for automatically learning this function from related classification problems. The parameter func- tion found by our algorithm then defines a new learning algorithm for text classification, which we can apply to novel classification tasks.

Is accurate classification possible in the absence of hand-labeled data? This paper introduces the Monotonic Feature (MF) abstraction--where the probability of class membership increases monotonically with the MF's value. The paper proves that when an MF is given, PAC learning is possible with no hand-labeled data under certain assumptions. We argue that MFs arise naturally in a broad range of textual classification applications. On the classic "20 Newsgroups" data set, a learner given an MF and unlabeled data achieves classification accuracy equal to that of a state-of-the-art semi-supervised learner relying on 160 hand-labeled examples.

Open-ended questions in surveys are valuable because they do not constrain the respondent's answer, thereby avoiding biases. However, answers to open-ended questions are text data which are harder to analyze. Traditionally, answers were manually classified as specified in the coding manual. Most of the effort to automate coding has gone into the easier problem of single label prediction, where answers are classified into a single code. However, open-ends that require multi-label classification, i.e., that are assigned multiple codes, occur frequently. This paper focuses on multi-label classification of text answers to open-ended survey questions in social science surveys. We evaluate the performance of the transformer-based architecture BERT for the German language in comparison to traditional multi-label algorithms (Binary Relevance, Label Powerset, ECC) in a German social science survey, the GLES Panel (N=17,584, 55 labels). We find that classification with BERT (forcing at least one label) has the smallest 0/1 loss (13.1%) among methods considered (18.9%-21.6%). As expected, it is much easier to correctly predict answer texts that correspond to a single label (7.1% loss) than those that correspond to multiple labels ($\sim$50% loss). Because BERT predicts zero labels for only 1.5% of the answers, forcing at least one label, while recommended, ultimately does not lower the 0/1 loss by much. Our work has important implications for social scientists: 1) We have shown multi-label classification with BERT works in the German language for open-ends. 2) For mildly multi-label classification tasks, the loss now appears small enough to allow for fully automatic classification (as compared to semi-automatic approaches). 3) Multi-label classification with BERT requires only a single model. The leading competitor, ECC, iterates through individual single label predictions.

Improving machine learning performance while increasing model generalization has been a constantly pursued goal by AI researchers. Data augmentation techniques are often used towards achieving this target, and most of its evaluation is made using English corpora. In this work, we took advantage of different existing data augmentation methods to analyze their performances applied to text classification problems using Brazilian Portuguese corpora. As a result, our analysis shows some putative improvements in using some of these techniques; however, it also suggests further exploitation of language bias and non-English text data scarcity.

Because of the inevitable cost and complexity of transformer and pre-trained models, efficiency concerns are raised for long text classification. Meanwhile, in the highly sensitive domains, e.g., healthcare and legal long-text mining, potential model distrust, yet underrated and underexplored, may hatch vital apprehension. Existing methods generally segment the long text, encode each piece with the pre-trained model, and use attention or RNNs to obtain long text representation for classification. In this work, we propose a simple but effective model, Segment-aWare multIdimensional PErceptron (SWIPE), to replace attention/RNNs in the above framework. Unlike prior efforts, SWIPE can effectively learn the label of the entire text with supervised training, while perceive the labels of the segments and estimate their contributions to the long-text labeling in an unsupervised manner. As a general classifier, SWIPE can endorse different encoders, and it outperforms SOTA models in terms of classification accuracy and model efficiency. It is noteworthy that SWIPE achieves superior interpretability to transparentize long text classification results.

In natural language processing, pre-trained language models have become essential infrastructures. However, these models often suffer from issues such as large size, long inference time, and challenging deployment. Moreover, most mainstream pre-trained models focus on English, and there are insufficient studies on small Chinese pre-trained models. In this paper, we introduce MiniRBT, a small Chinese pre-trained model that aims to advance research in Chinese natural language processing. MiniRBT employs a narrow and deep student model and incorporates whole word masking and two-stage distillation during pre-training to make it well-suited for most downstream tasks. Our experiments on machine reading comprehension and text classification tasks reveal that MiniRBT achieves 94% performance relative to RoBERTa, while providing a 6.8x speedup, demonstrating its effectiveness and efficiency.

For large-scale IT corpora with hundreds of classes organized in a hierarchy, the task of accurate classification of classes at the higher level in the hierarchies is crucial to avoid errors propagating to the lower levels. In the business world, an efficient and explainable ML model is preferred over an expensive black-box model, especially if the performance increase is marginal. A current trend in the Natural Language Processing (NLP) community is towards employing huge pre-trained language models (PLMs) or what is known as self-attention models (e.g., BERT) for almost any kind of NLP task (e.g., question-answering, sentiment analysis, text classification). Despite the widespread use of PLMs and the impressive performance in a broad range of NLP tasks, there is a lack of a clear and well-justified need to as why these models are being employed for domain-specific text classification (TC) tasks, given the monosemic nature of specialized words (i.e., jargon) found in domain-specific text which renders the purpose of contextualized embeddings (e.g., PLMs) futile. In this paper, we compare the accuracies of some state-of-the-art (SOTA) models reported in the literature against a Linear SVM classifier and TFIDF vectorization model on three TC datasets. Results show a comparable performance for the LinearSVM. The findings of this study show that for domain-specific TC tasks, a linear model can provide a comparable, cheap, reproducible, and interpretable alternative to attention-based models.

In the shipping industry, document classification plays a crucial role in ensuring that the necessary documents are properly identified and processed for customs clearance. OCR technology is being used to automate the process of document classification, which involves identifying important documents such as Commercial Invoices, Packing Lists, Export/Import Customs Declarations, Bills of Lading, Sea Waybills, Certificates, Air or Rail Waybills, Arrival Notices, Certificate of Origin, Importer Security Filings, and Letters of Credit. By using OCR technology, the shipping industry can improve accuracy and efficiency in document classification and streamline the customs clearance process. The aim of this study is to build a robust document classification system based on keyword frequencies. The research is carried out by analyzing Contract-Breach law documents available with IN-D. The documents were collected by scraping the Singapore Government Judiciary website. The database developed has 250 Contract-Breach documents. These documents are splitted to generate 200 training documents and 50 test documents. A semi-automatic approach is used to select keyword vectors for document classification. The accuracy of the reported model is 92.00 %.