More Like this

1. X-Class: Text Classification with Extremely Weak Supervision

   https://doi.org/10.18653/v1/2021.naacl-main.242  

   Wang, Zihan; Mekala, Dheeraj; Shang, Jingbo (January 2021, Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies)

   null (Ed.)

   In this paper, we explore text classification with extremely weak supervision, i.e., only relying on the surface text of class names. This is a more challenging setting than the seed-driven weak supervision, which allows a few seed words per class. We opt to attack this problem from a representation learning perspective—ideal document representations should lead to nearly the same results between clustering and the desired classification. In particular, one can classify the same corpus differently (e.g., based on topics and locations), so document representations should be adaptive to the given class names. We propose a novel framework X-Class to realize the adaptive representations. Specifically, we first estimate class representations by incrementally adding the most similar word to each class until inconsistency arises. Following a tailored mixture of class attention mechanisms, we obtain the document representation via a weighted average of contextualized word representations. With the prior of each document assigned to its nearest class, we then cluster and align the documents to classes. Finally, we pick the most confident documents from each cluster to train a text classifier. Extensive experiments demonstrate that X-Class can rival and even outperform seed-driven weakly supervised methods on 7 benchmark datasets. 

   more » « less
2. Text Classification Using Label Names Only: A Language Model Self-Training Approach

   https://doi.org/10.18653/v1/2020.emnlp-main.724  

   Meng, Yu; Zhang, Yunyi; Huang, Jiaxin; Xiong, Chenyan; Ji, Heng; Zhang, Chao; Han, Jiawei (January 2020, EMNLP'20: 2020 Conf. on Empirical Methods in Natural Language Processing, Nov. 2020)

   null (Ed.)

   Current text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. Hu-mans can perform classification without seeing any labeled examples but only based on a small set of words describing the categories to be classified. In this paper, we explore the potential of only using the label name of each class to train classification models on un-labeled data, without using any labeled documents. We use pre-trained neural language models both as general linguistic knowledge sources for category understanding and as representation learning models for document classification. Our method (1) associates semantically related words with the label names, (2) finds category-indicative words and trains the model to predict their implied categories, and (3) generalizes the model via self-training. We show that our model achieves around 90% ac-curacy on four benchmark datasets including topic and sentiment classification without using any labeled documents but learning from unlabeled data supervised by at most 3 words (1 in most cases) per class as the label name1. 

   more » « less
3. Robust Recurrent Classifier Chains for Multi-Label Learning with Missing Labels

   https://doi.org/10.1145/3511808.3557438  

   Gerych, Walter; Hartvigsen, Thomas; Buquicchio, Luke; Agu, Emmanuel; Rundensteiner, Elke (October 2022, 31st ACM International Conference on Information & Knowledge Management)

   Recurrent Classifier Chains (RCCs) are a leading approach for multi-label classification as they directly model the interdependencies between classes. Unfortunately, existing RCCs assume that every training instance is completely labeled with all its ground truth classes. In practice often only a subset of an instance's labels are annotated, while the annotations for other classes are missing. RCCs fail in this missing label scenario, predicting many false negatives and potentially missing important classes. In this work, we propose Robust-RCC, the first strategy for tackling this open problem of RCCs failing for multi-label missing-label data. Robust-RCC is a new type of deep recurrent classifier chain empowered to model inter-class relationships essential for predicting the complete label set most likely to match the ground truth. The key to Robust-RCC is the design of the Multi Incomplete Label Risk (MILR) function, which we prove to be equal in expectation to the true risk of the ground truth full label set despite being computed from incompletely labeled data. Our experimental study demonstrates that Robust-RCC consistently beats six state-of-of-the-art methods by as much as 30% in predicting the true labels. 

   more » « less
4. PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training

   https://doi.org/10.18653/v1/2023.emnlp-main.780  

   Zhang, Yunyi; Jiang, Minhao; Meng, Yu; Zhang, Yu; Han, Jiawei (January 2023, Association for Computational Linguistics)

   Weakly-supervised text classification trains a classifier using the label name of each target class as the only supervision, which largely reduces human annotation efforts. Most existing methods first use the label names as static keyword-based features to generate pseudo labels, which are then used for final classifier training. While reasonable, such a commonly adopted framework suffers from two limitations: (1) keywords can have different meanings in different contexts and some text may not have any keyword, so keyword matching can induce noisy and inadequate pseudo labels; (2) the errors made in the pseudo label generation stage will directly propagate to the classifier training stage without a chance of being corrected. In this paper, we propose a new method, PIEClass, consisting of two modules: (1) a pseudo label acquisition module that uses zero-shot prompting of pre-trained language models (PLM) to get pseudo labels based on contextualized text understanding beyond static keyword matching, and (2) a noise-robust iterative ensemble training module that iteratively trains classifiers and updates pseudo labels by utilizing two PLM fine-tuning methods that regularize each other. Extensive experiments show that PIEClass achieves overall better performance than existing strong baselines on seven benchmark datasets and even achieves similar performance to fully-supervised classifiers on sentiment classification tasks. 

   more » « less
5. Partial Domain Adaptation Using Selective Representation Learning For Class-Weight Computation

   https://doi.org/10.1109/IEEECONF51394.2020.9443420  

   Choudhuri, Sandipan; Paul, Riti; Sen, Arunabha; Li, Baoxin; Venkateswara, Hemanth (January 2020, 2020 54th Asilomar Conference on Signals, Systems, and Computers)

   Matthews, MB (Ed.)

   The generalization power of deep-learning models is dependent on rich-labelled data. This supervision using large-scaled annotated information is restrictive in most realworld scenarios where data collection and their annotation involve huge cost. Various domain adaptation techniques exist in literature that bridge this distribution discrepancy. However, a majority of these models require the label sets of both the domains to be identical. To tackle a more practical and challenging scenario, we formulate the problem statement from a partial domain adaptation perspective, where the source label set is a super set of the target label set. Driven by the motivation that image styles are private to each domain, in this work, we develop a method that identifies outlier classes exclusively from image content information and train a label classifier exclusively on class-content from source images. Additionally, elimination of negative transfer of samples from classes private to the source domain is achieved by transforming the soft class-level weights into two clusters, 0 (outlier source classes) and 1 (shared classes) by maximizing the between-cluster variance between them. 

   more » « less