The exponential growth of data generated on the Internet in the current information age is a driving force for the digital economy. Extraction of information is the major value in an accumulated big data. Big data dependency on statistical analysis and hand-engineered rules machine learning algorithms are overwhelmed with vast complexities inherent in human languages. Natural Language Processing (NLP) is equipping machines to understand these human diverse and complicated languages. Text Classification is an NLP task which automatically identifies patterns based on predefined or undefined labeled sets. Common text classification application includes information retrieval, modeling news topic, theme extraction, sentiment analysis, and spam detection. In texts, some sequences of words depend on the previous or next word sequences to make full meaning; this is a challenging dependency task that requires the machine to be able to store some previous important information to impact future meaning. Sequence models such as RNN, GRU, and LSTM is a breakthrough for tasks with long-range dependencies. As such, we applied these models to Binary and Multi-class classification. Results generated were excellent with most of the models performing within the range of 80% and 94%. However, this result is not exhaustive as we believe there is room for improvement if machines are to compete with humans.
In Natural Language Processing, the use of pre-trained language models has been shown to obtain state-of-the-art results in many downstream tasks such as sentiment analysis, author identification and others. In this work, we address the use of these methods for personality classification from text. Focusing on the Myers-Briggs (MBTI) personality model, we describe a series of experiments in which the well-known Bidirectional Encoder Representations from Transformers (BERT) model is fine-tuned to perform MBTI classification. Our main findings suggest that the current approach significantly outperforms well-known text classification models based on bag-of-words and static word embeddings alike across multiple evaluation scenarios, and generally outperforms previous work in the field.
While neural networks demonstrate a remarkable ability to model linguistic content, capturing contextual information related to a speaker's conversational role is an open area of research. In this work, we analyze the effect of speaker role on language use through the game of Mafia, in which participants are assigned either an honest or a deceptive role. In addition to building a framework to collect a dataset of Mafia game records, we demonstrate that there are differences in the language produced by players with different roles. We confirm that classification models are able to rank deceptive players as more suspicious than honest ones based only on their use of language. Furthermore, we show that training models on two auxiliary tasks outperforms a standard BERT-based text classification approach. We also present methods for using our trained models to identify features that distinguish between player roles, which could be used to assist players during the Mafia game.
We apply methods of topological analysis to the attention graphs, calculated on the attention heads of the BERT model ( arXiv:1810.04805v2 ). Our research shows that the classifier built upon basic persistent topological features (namely, Betti numbers) of the trained neural network can achieve classification results on par with the conventional classification method. We show the relevance of such topological text representation on three text classification benchmarks. For the best of our knowledge, it is the first attempt to analyze the topology of an attention-based neural network, widely used for Natural Language Processing.
Following how humans communicate, free-text rationales aim to use natural language to explain neural language model (LM) behavior. However, free-text rationales' unconstrained nature makes them prone to hallucination, so it is important to have metrics for free-text rationale quality. Existing free-text rationale metrics measure how consistent the rationale is with the LM's predicted label, but there is no protocol for assessing such metrics' reliability. Thus, we propose FRAME, a framework for evaluating rationale-label consistency (RLC) metrics for free-text rationales. FRAME is based on three axioms: (1) good metrics should yield highest scores for reference rationales, which maximize RLC by construction; (2) good metrics should be appropriately sensitive to semantic perturbation of rationales; and (3) good metrics should be robust to variation in the LM's task performance. Across three text classification datasets, we show that existing RLC metrics cannot satisfy all three FRAME axioms, since they are implemented via model pretraining which muddles the metric's signal. Then, we introduce a non-pretraining RLC metric that greatly outperforms baselines on (1) and (3), while performing competitively on (2). Finally, we discuss the limitations of using RLC to evaluate free-text rationales.
The COVID-19 pandemic has caused globally significant impacts since the beginning of 2020. This brought a lot of confusion to society, especially due to the spread of misinformation through social media. Although there were already several studies related to the detection of misinformation in social media data, most studies focused on the English dataset. Research on COVID-19 misinformation detection in Indonesia is still scarce. Therefore, through this research, we collect and annotate datasets for Indonesian and build prediction models for detecting COVID-19 misinformation by considering the tweet's relevance. The dataset construction is carried out by a team of annotators who labeled the relevance and misinformation of the tweet data. In this study, we propose the two-stage classifier model using IndoBERT pre-trained language model for the Tweet misinformation detection task. We also experiment with several other baseline models for text classification. The experimental results show that the combination of the BERT sequence classifier for relevance prediction and Bi-LSTM for misinformation detection outperformed other machine learning models with an accuracy of 87.02%. Overall, the BERT utilization contributes to the higher performance of most prediction models. We release a high-quality COVID-19 misinformation Tweet corpus in the Indonesian language, indicated by the high inter-annotator agreement.
In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is known as catastrophic forgetting and it is often difficult to prevent due to practical constraints, such as the amount of data that can be stored or the limited computation sources that can be used. Moreover, training large neural networks, such as Transformers, from scratch is very costly and requires a vast amount of training data, which might not be available in the application domain of interest. A recent trend indicates that dynamic architectures based on an expansion of the parameters can reduce catastrophic forgetting efficiently in continual learning, but this needs complex tuning to balance the growing number of parameters and barely share any information across tasks. As a result, they struggle to scale to a large number of tasks without significant overhead. In this paper, we validate in the computer vision domain a recent solution called Adaptive Distillation of Adapters (ADA), which is developed to perform continual learning using pre-trained Transformers and Adapters on text classification tasks. We empirically demonstrate on different classification tasks that this method maintains a good predictive performance without retraining the model or increasing the number of model parameters over the time. Besides it is significantly faster at inference time compared to the state-of-the-art methods.
Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model performance post-hoc, without additional training. Although test-time augmentation (TTA) can be applied to any data modality, it has seen limited adoption in NLP due in part to the difficulty of identifying label-preserving transformations. In this paper, we present augmentation policies that yield significant accuracy improvements with language models. A key finding is that augmentation policy design -- for instance, the number of samples generated from a single, non-deterministic augmentation -- has a considerable impact on the benefit of TTA. Experiments across a binary classification task and dataset show that test-time augmentation can deliver consistent improvements over current state-of-the-art approaches.
In recent years, predictive machine learning methods have gained prominence in various scientific domains. However, due to their black-box nature, it is essential to establish trust in these models before accepting them as accurate. One promising strategy for assigning trust involves employing explanation techniques that elucidate the rationale behind a black-box model's predictions in a manner that humans can understand. However, assessing the degree of human interpretability of the rationale generated by such methods is a nontrivial challenge. In this work, we introduce interpretation entropy as a universal solution for assessing the degree of human interpretability associated with any linear model. Using this concept and drawing inspiration from classical thermodynamics, we present Thermodynamics-inspired Explainable Representations of AI and other black-box Paradigms (TERP), a method for generating accurate, and human-interpretable explanations for black-box predictions in a model-agnostic manner. To demonstrate the wide-ranging applicability of TERP, we successfully employ it to explain various black-box model architectures, including deep learning Autoencoders, Recurrent Neural Networks, and Convolutional Neural Networks, across diverse domains such as molecular simulations, text, and image classification.
Text classification plays an important role in many practical applications. In the real world, there are extremely small datasets. Most existing methods adopt pre-trained neural network models to handle this kind of dataset. However, these methods are either difficult to deploy on mobile devices because of their large output size or cannot fully extract the deep semantic information between phrases and clauses. This paper proposes a multimodel-based deep learning framework for short-text multiclass classification with an imbalanced and extremely small data set. Our framework mainly includes five layers: The encoder layer uses DISTILBERT to obtain context-sensitive dynamic word vectors that are difficult to represent in traditional feature engineering methods. Since the transformer part of this layer is distilled, our framework is compressed. Then, we use the next two layers to extract deep semantic information. The output of the encoder layer is sent to a bidirectional LSTM network, and the feature matrix is extracted hierarchically through the LSTM at the word and sentence level to obtain the fine-grained semantic representation. After that, the max-pooling layer converts the feature matrix into a lower-dimensional matrix, preserving only the obvious features. Finally, the feature matrix is taken as the input of a fully connected softmax layer, which contains a function that can convert the predicted linear vector into the output value as the probability of the text in each classification. Extensive experiments on two public benchmarks demonstrate the effectiveness of our proposed approach on an extremely small data set. It retains the state-of-the-art baseline performance in terms of precision, recall, accuracy, and F1 score, and through the model size, training time, and convergence epoch, we can conclude that our method can be deployed faster and lighter on mobile devices.
Deep neural networks (DNNs) have a high capacity to completely memorize noisy labels given sufficient training time, and its memorization, unfortunately, leads to performance degradation. Recently, virtual adversarial training (VAT) attracts attention as it could further improve the generalization of DNNs in semi-supervised learning. The driving force behind VAT is to prevent the models from overfitting data points by enforcing consistency between the inputs and the perturbed inputs. This strategy could be helpful in learning from noisy labels if it prevents neural models from learning noisy samples while encouraging the models to generalize clean samples. In this paper, we propose context-based virtual adversarial training (ConVAT) to prevent a text classifier from overfitting to noisy labels. Unlike the previous works, the proposed method performs the adversarial training at the context level rather than the inputs. It makes the classifier not only learn its label but also its contextual neighbors, which alleviates the learning from noisy labels by preserving contextual semantics on each data point. We conduct extensive experiments on four text classification datasets with two types of label noises. Comprehensive experimental results clearly show that the proposed method works quite well even with extremely noisy settings.
The recent advances in transfer learning techniques and pre-training of large contextualized encoders foster innovation in real-life applications, including dialog assistants. Practical needs of intent recognition require effective data usage and the ability to constantly update supported intents, adopting new ones, and abandoning outdated ones. In particular, the generalized zero-shot paradigm, in which the model is trained on the seen intents and tested on both seen and unseen intents, is taking on new importance. In this paper, we explore the generalized zero-shot setup for intent recognition. Following best practices for zero-shot text classification, we treat the task with a sentence pair modeling approach. We outperform previous state-of-the-art f1-measure by up to 16\% for unseen intents, using intent labels and user utterances and without accessing external sources (such as knowledge bases). Further enhancement includes lexicalization of intent labels, which improves performance by up to 7\%. By using task transferring from other sentence pair tasks, such as Natural Language Inference, we gain additional improvements.
Domain adaptive text classification is a challenging problem for the large-scale pretrained language models because they often require expensive additional labeled data to adapt to new domains. Existing works usually fails to leverage the implicit relationships among words across domains. In this paper, we propose a novel method, called Domain Adaptation with Structured Knowledge (DASK), to enhance domain adaptation by exploiting word-level semantic relationships. DASK first builds a knowledge graph to capture the relationship between pivot terms (domain-independent words) and non-pivot terms in the target domain. Then during training, DASK injects pivot-related knowledge graph information into source domain texts. For the downstream task, these knowledge-injected texts are fed into a BERT variant capable of processing knowledge-injected textual data. Thanks to the knowledge injection, our model learns domain-invariant features for non-pivots according to their relationships with pivots. DASK ensures the pivots to have domain-invariant behaviors by dynamically inferring via the polarity scores of candidate pivots during training with pseudo-labels. We validate DASK on a wide range of cross-domain sentiment classification tasks and observe up to 2.9% absolute performance improvement over baselines for 20 different domain pairs. Code will be made available at https://github.com/hikaru-nara/DASK.
The rapid development of deep natural language processing (NLP) models for text classification has led to an urgent need for a unified understanding of these models proposed individually. Existing methods cannot meet the need for understanding different models in one framework due to the lack of a unified measure for explaining both low-level (e.g., words) and high-level (e.g., phrases) features. We have developed a visual analysis tool, DeepNLPVis, to enable a unified understanding of NLP models for text classification. The key idea is a mutual information-based measure, which provides quantitative explanations on how each layer of a model maintains the information of input words in a sample. We model the intra- and inter-word information at each layer measuring the importance of a word to the final prediction as well as the relationships between words, such as the formation of phrases. A multi-level visualization, which consists of a corpus-level, a sample-level, and a word-level visualization, supports the analysis from the overall training set to individual samples. Two case studies on classification tasks and comparison between models demonstrate that DeepNLPVis can help users effectively identify potential problems caused by samples and model architectures and then make informed improvements.
Text Classification is an integral part of many Natural Language Processing tasks such as sarcasm detection, sentiment analysis and many more such applications. Many e-commerce websites, social-media/entertainment platforms use such models to enhance user-experience to generate traffic and thus, revenue on their platforms. In this paper, we are presenting our solution to Multilingual Abusive Comment Identification Problem on Moj, an Indian video-sharing social networking service, powered by ShareChat. The problem dealt with detecting abusive comments, in 13 regional Indic languages such as Hindi, Telugu, Kannada etc., on the videos on Moj platform. Our solution utilizes the novel muBoost, an ensemble of CatBoost classifier models and Multilingual Representations for Indian Languages (MURIL) model, to produce SOTA performance on Indic text classification tasks. We were able to achieve a mean F1-score of 89.286 on the test data, an improvement over baseline MURIL model with a F1-score of 87.48.
For preventing youth suicide, social media platforms have received much attention from researchers. A few researches apply machine learning, or deep learning-based text classification approaches to classify social media posts containing suicidality risk. This paper replicated competitive social media-based suicidality detection/prediction models. We evaluated the feasibility of detecting suicidal ideation using multiple datasets and different state-of-the-art deep learning models, RNN-, CNN-, and Attention-based models. Using two suicidality evaluation datasets, we evaluated 28 combinations of 7 input embeddings with 4 commonly used deep learning models and 5 pretrained language models in quantitative and qualitative ways. Our replication study confirms that deep learning works well for social media-based suicidality detection in general, but it highly depends on the dataset's quality.
Large-scale pre-trained language models (PLMs) are well-known for being capable of solving a task simply by conditioning a few input-label pairs dubbed demonstrations on a prompt without being explicitly tuned for the desired downstream task. Such a process (i.e., in-context learning), however, naturally leads to high reliance on the demonstrations which are usually selected from external datasets. In this paper, we propose self-generated in-context learning (SG-ICL), which generates demonstrations for in-context learning from PLM itself to minimize the reliance on the external demonstration. We conduct experiments on four different text classification tasks and show SG-ICL significantly outperforms zero-shot learning and is generally worth approximately 0.6 gold training samples. Moreover, our generated demonstrations show more consistent performance with low variance compared to randomly selected demonstrations from the training dataset.
Genre identification is a subclass of non-topical text classification. The main difference between this task and topical classification is that genres, unlike topics, usually do not correspond to simple keywords, and thus they need to be defined in terms of their functions in communication. Neural models based on pre-trained transformers, such as BERT or XLM-RoBERTa, demonstrate SOTA results in many NLP tasks, including non-topical classification. However, in many cases, their downstream application to very large corpora, such as those extracted from social media, can lead to unreliable results because of dataset shifts, when some raw texts do not match the profile of the training set. To mitigate this problem, we experiment with individual models as well as with their ensembles. To evaluate the robustness of all models we use a prediction confidence metric, which estimates the reliability of a prediction in the absence of a gold standard label. We can evaluate robustness via the confidence gap between the correctly classified texts and the misclassified ones on a labeled test corpus, higher gaps make it easier to improve our confidence that our classifier made the right decision. Our results show that for all of the classifiers tested in this study, there is a confidence gap, but for the ensembles, the gap is bigger, meaning that ensembles are more robust than their individual models.
The advent of large-scale pre-trained language models has contributed greatly to the recent progress in natural language processing. Many state-of-the-art language models are first trained on a large text corpus and then fine-tuned on downstream tasks. Despite its recent success and wide adoption, fine-tuning a pre-trained language model often suffers from overfitting, which leads to poor generalizability due to the extremely high complexity of the model and the limited training samples from downstream tasks. To address this problem, we propose a novel and effective fine-tuning framework, named Layerwise Noise Stability Regularization (LNSR). Specifically, we propose to inject the standard Gaussian noise or In-manifold noise and regularize hidden representations of the fine-tuned model. We first provide theoretical analyses to support the efficacy of our method. We then demonstrate the advantages of the proposed method over other state-of-the-art algorithms including L2-SP, Mixout and SMART. While these previous works only verify the effectiveness of their methods on relatively simple text classification tasks, we also verify the effectiveness of our method on question answering tasks, where the target problem is much more difficult and more training examples are available. Furthermore, extensive experimental results indicate that the proposed algorithm can not only enhance the in-domain performance of the language models but also improve the domain generalization performance on out-of-domain data.
The most prominent tasks in emotion analysis are to assign emotions to texts and to understand how emotions manifest in language. An observation for NLP is that emotions can be communicated implicitly by referring to events, appealing to an empathetic, intersubjective understanding of events, even without explicitly mentioning an emotion name. In psychology, the class of emotion theories known as appraisal theories aims at explaining the link between events and emotions. Appraisals can be formalized as variables that measure a cognitive evaluation by people living through an event that they consider relevant. They include the assessment if an event is novel, if the person considers themselves to be responsible, if it is in line with the own goals, and many others. Such appraisals explain which emotions are developed based on an event, e.g., that a novel situation can induce surprise or one with uncertain consequences could evoke fear. We analyze the suitability of appraisal theories for emotion analysis in text with the goal of understanding if appraisal concepts can reliably be reconstructed by annotators, if they can be predicted by text classifiers, and if appraisal concepts help to identify emotion categories. To achieve that, we compile a corpus by asking people to textually describe events that triggered particular emotions and to disclose their appraisals. Then, we ask readers to reconstruct emotions and appraisals from the text. This setup allows us to measure if emotions and appraisals can be recovered purely from text and provides a human baseline. Our comparison of text classification methods to human annotators shows that both can reliably detect emotions and appraisals with similar performance. Therefore, appraisals constitute an alternative computational emotion analysis paradigm and further improve the categorization of emotions in text with joint models.