In natural language processing, extreme multi-label text classification is an emerging but essential task. The problem of extreme multi-label text classification (XMTC) is to recall some of the most relevant labels for a text from an extremely large label set. Large-scale pre-trained models have brought a new trend to this problem. Though the large-scale pre-trained models have made significant achievements on this problem, the valuable fine-tuned methods have yet to be studied. Though label semantics have been introduced in XMTC, the vast semantic gap between texts and labels has yet to gain enough attention. This paper builds a new guide network (GUDN) to help fine-tune the pre-trained model to instruct classification later. Furthermore, GUDN uses raw label semantics combined with a helpful label reinforcement strategy to effectively explore the latent space between texts and labels, narrowing the semantic gap, which can further improve predicted accuracy. Experimental results demonstrate that GUDN outperforms state-of-the-art methods on Eurlex-4k and has competitive results on other popular datasets. In an additional experiment, we investigated the input lengths' influence on the Transformer-based model's accuracy. Our source code is released at https://t.hk.uy/aFSH.
Large pretrained language models (LMs) like BERT have improved performance in many disparate natural language processing (NLP) tasks. However, fine tuning such models requires a large number of training examples for each target task. Simultaneously, many realistic NLP problems are "few shot", without a sufficiently large training set. In this work, we propose a novel conditional neural process-based approach for few-shot text classification that learns to transfer from other diverse tasks with rich annotation. Our key idea is to represent each task using gradient information from a base model and to train an adaptation network that modulates a text classifier conditioned on the task representation. While previous task-aware few-shot learners represent tasks by input encoding, our novel task representation is more powerful, as the gradient captures input-output relationships of a task. Experimental results show that our approach outperforms traditional fine-tuning, sequential transfer learning, and state-of-the-art meta learning approaches on a collection of diverse few-shot tasks. We further conducted analysis and ablations to justify our design choices.
Many companies nowadays offer compensation to online reviews (called compensated reviews), expecting to increase the volume of their non-compensated reviews and overall rating. Does this strategy work? On what subjects or topics does this strategy work the best? These questions have still not been answered in the literature but draw substantial interest from the industry. In this paper, we study the effect of compensated reviews on non-compensated reviews by utilizing online reviews on 1,240 auto shipping companies over a ten-year period from a transportation website. Because some online reviews have missing information on their compensation status, we first develop a classification algorithm to differentiate compensated reviews from non-compensated reviews by leveraging a machine learning-based identification process, drawing upon the unique features of the compensated reviews. From the classification results, we empirically investigate the effects of compensated reviews on non-compensated. Our results indicate that the number of compensated reviews does indeed increase the number of non-compensated reviews. In addition, the ratings of compensated reviews positively affect the ratings of non-compensated reviews. Moreover, if the compensated reviews feature the topic or subject of a car shipping function, the positive effect of compensated reviews on non-compensated ones is the strongest. Besides methodological contributions in text classification and empirical modeling, our study provides empirical evidence on how to prove the effectiveness of compensated online reviews in terms of improving the platform's overall online reviews and ratings. Also, it suggests a guideline for utilizing compensated reviews to their full strength, that is, with regard to featuring certain topics or subjects in these reviews to achieve the best outcome.
Natural language inference (NLI) is an increasingly important task for natural language understanding, which requires one to infer the relationship between the sentence pair (premise and hypothesis). Many recent works have used contrastive learning by incorporating the relationship of the sentence pair from NLI datasets to learn sentence representation. However, these methods only focus on comparisons with sentence-level representations. In this paper, we propose a Pair-level Supervised Contrastive Learning approach (PairSCL). We adopt a cross attention module to learn the joint representations of the sentence pairs. A contrastive learning objective is designed to distinguish the varied classes of sentence pairs by pulling those in one class together and pushing apart the pairs in other classes. We evaluate PairSCL on two public datasets of NLI where the accuracy of PairSCL outperforms other methods by 2.1% on average. Furthermore, our method outperforms the previous state-of-the-art method on seven transfer tasks of text classification.
Social media platforms have transformed traditional communication methods by allowing users worldwide to communicate instantly, openly, and frequently. People use social media to express their opinion and share their personal stories and struggles. Negative feelings that express hardship, thoughts of death, and self-harm are widespread in social media, especially among young generations. Therefore, using social media to detect and identify suicidal ideation will help provide proper intervention that will eventually dissuade others from self-harming and committing suicide and prevent the spread of suicidal ideations on social media. Many studies have been carried out to identify suicidal ideation and behaviors in social media. This paper presents a comprehensive summary of current research efforts to detect suicidal ideation using machine learning algorithms on social media. This review 24 studies investigating the feasibility of social media usage for suicidal ideation detection is intended to facilitate further research in the field and will be a beneficial resource for researchers engaged in suicidal text classification.
Over the last few years, Text classification is one of the fundamental tasks in natural language processing (NLP) in which the objective is to categorize text documents into one of the predefined classes. The news is full of our life. Therefore, news headlines classification is a crucial task to connect users with the right news. The news headline classification is a kind of text classification, which can be generally divided into three mainly parts: feature extraction, classifier selection, and evaluations. In this article, we use the dataset, containing news over a period of eighteen years provided by Kaggle platform to classify news headlines. We choose TF-IDF to extract features and neural network as the classifier, while the evaluation metrics is accuracy. From the experiment result, it is obvious that our NN model has the best performance among these models in the metrics of accuracy. The higher the accuracy is, the better performance the model will gain. Our NN model owns the accuracy 0.8622, which is highest accuracy among these four models. And it is 0.0134, 0.033, 0.080 higher than its of other models.
The increasing scale of general-purpose Pre-trained Language Models (PLMs) necessitates the study of more efficient adaptation across different downstream tasks. In this paper, we establish a Black-box Discrete Prompt Learning (BDPL) to resonate with pragmatic interactions between the cloud infrastructure and edge devices. Particularly, instead of fine-tuning the model in the cloud, we adapt PLMs by prompt learning, which efficiently optimizes only a few parameters of the discrete prompts. Moreover, we consider the scenario that we do not have access to the parameters and gradients of the pre-trained models, except for its outputs given inputs. This black-box setting secures the cloud infrastructure from potential attack and misuse to cause a single-point failure, which is preferable to the white-box counterpart by current infrastructures. Under this black-box constraint, we apply a variance-reduced policy gradient algorithm to estimate the gradients of parameters in the categorical distribution of each discrete prompt. In light of our method, the user devices can efficiently tune their tasks by querying the PLMs bounded by a range of API calls. Our experiments on RoBERTa and GPT-3 demonstrate that the proposed algorithm achieves significant improvement on eight benchmarks in a cloud-device collaboration manner. Finally, we conduct in-depth case studies to comprehensively analyze our method in terms of various data sizes, prompt lengths, training budgets, optimization objectives, prompt transferability, and explanations of the learned prompts. Our code will be available at https://github.com/shizhediao/Black-Box-Prompt-Learning.
Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in practice. In this work, we introduce a dual contrastive learning (DualCL) framework that simultaneously learns the features of input samples and the parameters of classifiers in the same space. Specifically, DualCL regards the parameters of the classifiers as augmented samples associating to different labels and then exploits the contrastive learning between the input samples and the augmented samples. Empirical studies on five benchmark text classification datasets and their low-resource version demonstrate the improvement in classification accuracy and confirm the capability of learning discriminative representations of DualCL.
Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications. To this end, we consider a rarely investigated but more rigorous setting, namely hard-label attack, in which the attacker can only access the prediction label. In particular, we find we can learn the importance of different words via the change on prediction label caused by word substitutions on the adversarial examples. Based on this observation, we propose a novel adversarial attack, termed Text Hard-label attacker (TextHacker). TextHacker randomly perturbs lots of words to craft an adversarial example. Then, TextHacker adopts a hybrid local search algorithm with the estimation of word importance from the attack history to minimize the adversarial perturbation. Extensive evaluations for text classification and textual entailment show that TextHacker significantly outperforms existing hard-label attacks regarding the attack performance as well as adversary quality.
Unsupervised domain adaptation (UDA) generally aligns the unlabeled target domain data to the distribution of the source domain to mitigate the distribution shift problem. The standard UDA requires sharing the source data with the target, having potential data privacy leaking risks. To protect the source data's privacy, we first propose to share the source feature distribution instead of the source data. However, sharing only the source feature distribution may still suffer from the membership inference attack who can infer an individual's membership by the black-box access to the source model. To resolve this privacy issue, we further study the under-explored problem of privacy-preserving domain adaptation and propose a method with a novel differential privacy training strategy to protect the source data privacy. We model the source feature distribution by Gaussian Mixture Models (GMMs) under the differential privacy setting and send it to the target client for adaptation. The target client resamples differentially private source features from GMMs and adapts on target data with several state-of-art UDA backbones. With our proposed method, the source data provider could avoid leaking source data privacy during domain adaptation as well as reserve the utility. To evaluate our proposed method's utility and privacy loss, we apply our model on a medical report disease label classification task using two noisy challenging clinical text datasets. The results show that our proposed method can preserve source data's privacy with a minor performance influence on the text classification task.
Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve complex problems and to build AI systems nowadays and especially in those cases where we have tacit knowledge or the knowledge that is not known. We used machine learning algorithms and for identification of fake news; we applied three classifiers; Passive Aggressive, Na\"ive Bayes, and Support Vector Machine. Simple classification is not completely correct in fake news detection because classification methods are not specialized for fake news. With the integration of machine learning and text-based processing, we can detect fake news and build classifiers that can classify the news data. Text classification mainly focuses on extracting various features of text and after that incorporating those features into classification. The big challenge in this area is the lack of an efficient way to differentiate between fake and non-fake due to the unavailability of corpora. We applied three different machine learning classifiers on two publicly available datasets. Experimental analysis based on the existing dataset indicates a very encouraging and improved performance.
Several complex systems are characterized by presenting intricate characteristics taking place at several scales of time and space. These multiscale characterizations are used in various applications, including better understanding diseases, characterizing transportation systems, and comparison between cities, among others. In particular, texts are also characterized by a hierarchical structure that can be approached by using multi-scale concepts and methods. The multiscale properties of texts constitute a subject worth further investigation. In addition, more effective approaches to text characterization and analysis can be obtained by emphasizing words with potentially more informational content. The present work aims at developing these possibilities while focusing on mesoscopic representations of networks. More specifically, we adopt an extension to the mesoscopic approach to represent text narratives, in which only the recurrent relationships among tagged parts of speech (subject, verb and direct object) are considered to establish connections among sequential pieces of text (e.g., paragraphs). The characterization of the texts was then achieved by considering scale-dependent complementary methods: accessibility, symmetry and recurrence signatures. In order to evaluate the potential of these concepts and methods, we approached the problem of distinguishing between literary genres (fiction and non-fiction). A set of 300 books organized into the two genres was considered and were compared by using the aforementioned approaches. All the methods were capable of differentiating to some extent between the two genres. The accessibility and symmetry reflected the narrative asymmetries, while the recurrence signature provided a more direct indication about the non-sequential semantic connections taking place along the narrative.
In this paper, we study the "stability" of machine learning (ML) models within the context of larger, complex NLP systems with continuous training data updates. For this study, we propose a methodology for the assessment of model stability (which we refer to as jitter under various experimental conditions. We find that model design choices, including network architecture and input representation, have a critical impact on stability through experiments on four text classification tasks and two sequence labeling tasks. In classification tasks, non-RNN-based models are observed to be more stable than RNN-based ones, while the encoder-decoder model is less stable in sequence labeling tasks. Moreover, input representations based on pre-trained fastText embeddings contribute to more stability than other choices. We also show that two learning strategies -- ensemble models and incremental training -- have a significant influence on stability. We recommend ML model designers account for trade-offs in accuracy and jitter when making modeling choices.
Text classification algorithms investigate the intricate relationships between words or phrases and attempt to deduce the document's interpretation. In the last few years, these algorithms have progressed tremendously. Transformer architecture and sentence encoders have proven to give superior results on natural language processing tasks. But a major limitation of these architectures is their applicability for text no longer than a few hundred words. In this paper, we explore hierarchical transfer learning approaches for long document classification. We employ pre-trained Universal Sentence Encoder (USE) and Bidirectional Encoder Representations from Transformers (BERT) in a hierarchical setup to capture better representations efficiently. Our proposed models are conceptually simple where we divide the input data into chunks and then pass this through base models of BERT and USE. Then output representation for each chunk is then propagated through a shallow neural network comprising of LSTMs or CNNs for classifying the text data. These extensions are evaluated on 6 benchmark datasets. We show that USE + CNN/LSTM performs better than its stand-alone baseline. Whereas the BERT + CNN/LSTM performs on par with its stand-alone counterpart. However, the hierarchical BERT models are still desirable as it avoids the quadratic complexity of the attention mechanism in BERT. Along with the hierarchical approaches, this work also provides a comparison of different deep learning algorithms like USE, BERT, HAN, Longformer, and BigBird for long document classification. The Longformer approach consistently performs well on most of the datasets.
The paper describes the open Russian medical language understanding benchmark covering several task types (classification, question answering, natural language inference, named entity recognition) on a number of novel text sets. Given the sensitive nature of the data in healthcare, such a benchmark partially closes the problem of Russian medical dataset absence. We prepare the unified format labeling, data split, and evaluation metrics for new tasks. The remaining tasks are from existing datasets with a few modifications. A single-number metric expresses a model's ability to cope with the benchmark. Moreover, we implement several baseline models, from simple ones to neural networks with transformer architecture, and release the code. Expectedly, the more advanced models yield better performance, but even a simple model is enough for a decent result in some tasks. Furthermore, for all tasks, we provide a human evaluation. Interestingly the models outperform humans in the large-scale classification tasks. However, the advantage of natural intelligence remains in the tasks requiring more knowledge and reasoning.
Active learning is an increasingly important branch of machine learning and a powerful technique for natural language processing. The main advantage of active learning is its potential to reduce the amount of labeled data needed to learn high-performing models. A vital aspect of an effective active learning algorithm is the determination of when to stop obtaining additional labeled data. Several leading state-of-the-art stopping methods use a stop set to help make this decision. However, there has been relatively less attention given to the choice of stop set than to the stopping algorithms that are applied on the stop set. Different choices of stop sets can lead to significant differences in stopping method performance. We investigate the impact of different stop set choices on different stopping methods. This paper shows the choice of the stop set can have a significant impact on the performance of stopping methods and the impact is different for stability-based methods from that on confidence-based methods. Furthermore, the unbiased representative stop sets suggested by original authors of methods work better than the systematically biased stop sets used in recently published work, and stopping methods based on stabilizing predictions have stronger performance than confidence-based stopping methods when unbiased representative stop sets are used. We provide the largest quantity of experimental results on the impact of stop sets to date. The findings are important for helping to illuminate the impact of this important aspect of stopping methods that has been under-considered in recently published work and that can have a large practical impact on the performance of stopping methods for important semantic computing applications such as technology assisted review and text classification more broadly.
Recent advances on prompt-tuning cast few-shot classification tasks as a masked language modeling problem. By wrapping input into a template and using a verbalizer which constructs a mapping between label space and label word space, prompt-tuning can achieve excellent results in zero-shot and few-shot scenarios. However, typical prompt-tuning needs a manually designed verbalizer which requires domain expertise and human efforts. And the insufficient label space may introduce considerable bias into the results. In this paper, we focus on eliciting knowledge from pretrained language models and propose a prototypical prompt verbalizer for prompt-tuning. Labels are represented by prototypical embeddings in the feature space rather than by discrete words. The distances between the embedding at the masked position of input and prototypical embeddings are used as classification criterion. For zero-shot settings, knowledge is elicited from pretrained language models by a manually designed template to form initial prototypical embeddings. For few-shot settings, models are tuned to learn meaningful and interpretable prototypical embeddings. Our method optimizes models by contrastive learning. Extensive experimental results on several many-class text classification datasets with low-resource settings demonstrate the effectiveness of our approach compared with other verbalizer construction methods. Our implementation is available at https://github.com/Ydongd/prototypical-prompt-verbalizer.
The Gutenberg Literary English Corpus (GLEC, Jacobs, 2018a) provides a rich source of textual data for research in digital humanities, computational linguistics or neurocognitive poetics. In this study we address differences among the different literature categories in GLEC, as well as differences between authors. We report the results of three studies providing i) topic and sentiment analyses for six text categories of GLEC (i.e., children and youth, essays, novels, plays, poems, stories) and its >100 authors, ii) novel measures of semantic complexity as indices of the literariness, creativity and book beauty of the works in GLEC (e.g., Jane Austen's six novels), and iii) two experiments on text classification and authorship recognition using novel features of semantic complexity. The data on two novel measures estimating a text's literariness, intratextual variance and stepwise distance (van Cranenburgh et al., 2019) revealed that plays are the most literary texts in GLEC, followed by poems and novels. Computation of a novel index of text creativity (Gray et al., 2016) revealed poems and plays as the most creative categories with the most creative authors all being poets (Milton, Pope, Keats, Byron, or Wordsworth). We also computed a novel index of perceived beauty of verbal art (Kintsch, 2012) for the works in GLEC and predict that Emma is the theoretically most beautiful of Austen's novels. Finally, we demonstrate that these novel measures of semantic complexity are important features for text classification and authorship recognition with overall predictive accuracies in the range of .75 to .97. Our data pave the way for future computational and empirical studies of literature or experiments in reading psychology and offer multiple baselines and benchmarks for analysing and validating other book corpora.
BERT has revolutionized the NLP field by enabling transfer learning with large language models that can capture complex textual patterns, reaching the state-of-the-art for an expressive number of NLP applications. For text classification tasks, BERT has already been extensively explored. However, aspects like how to better cope with the different embeddings provided by the BERT output layer and the usage of language-specific instead of multilingual models are not well studied in the literature, especially for the Brazilian Portuguese language. The purpose of this article is to conduct an extensive experimental study regarding different strategies for aggregating the features produced in the BERT output layer, with a focus on the sentiment analysis task. The experiments include BERT models trained with Brazilian Portuguese corpora and the multilingual version, contemplating multiple aggregation strategies and open-source datasets with predefined training, validation, and test partitions to facilitate the reproducibility of the results. BERT achieved the highest ROC-AUC values for the majority of cases as compared to TF-IDF. Nonetheless, TF-IDF represents a good trade-off between the predictive performance and computational cost.
It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threatening backdoor attack is the stealthy backdoor, which defines the triggers as text style or syntactic. Although they have achieved an incredible high attack success rate (ASR), we find that the principal factor contributing to their ASR is not the `backdoor trigger' paradigm. Thus the capacity of these stealthy backdoor attacks is overestimated when categorized as backdoor attacks. Therefore, to evaluate the real attack power of backdoor attacks, we propose a new metric called attack successful rate difference (ASRD), which measures the ASR difference between clean state and poison state models. Besides, since the defenses against stealthy backdoor attacks are absent, we propose Trigger Breaker, consisting of two too simple tricks that can defend against stealthy backdoor attacks effectively. Experiments show that our method achieves significantly better performance than state-of-the-art defense methods against stealthy backdoor attacks.