Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWeakly-supervised Text Classification Based on Keyword Graph
تصنيف النص الأكثر إشرافا ضعيفا بناء على الرسم البياني الكلمة الرئيسية
447
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تلقت تصنيف النص الإشراف ضعيف اهتماما كبيرا في السنوات الأخيرة لأنه يمكن أن يخفف من العبء الثقيل في التخلص من البيانات الضخمة. من بينها، الأساليب التي يحركها الكلمات الرئيسية هي السائدة حيث يتم استغلال الكلمات الرئيسية التي توفرها المستخدم لتوليد ملصقات زائفة للنصوص غير المسبقة. ومع ذلك، فإن الطرق الحالية تعالج الكلمات الرئيسية بشكل مستقل، وبالتالي تجاهل الارتباط بينها، والتي ينبغي أن تكون مفيدة إذا استغلت بشكل صحيح. في هذه الورقة، نقترح إطارا جديدا يسمى ClassKG لاستكشاف ارتباط الكلمات الرئيسية الكلمة الرئيسية على الرسم البياني للكلمة الرئيسية بواسطة GNN. إطار عملنا هو عملية تكرارية. في كل تكرار، نقوم أولا بإنشاء رسم بياني للكلمات الرئيسية، لذلك يتم تحويل مهمة تعيين ملصقات زائفة إلى التسجيل عبر الكلمات الرئيسية. لتحسين جودة التعليق التوضيحي، نقدم مهمة ذاتية الإشراف على الصنع بتقسيم Annetator Sigcraph، ثم Finetune IT. باستخدام الملصقات الزائفة التي تم إنشاؤها بواسطة Annotator Siggraph، ثم تدريب مصنف نصي لتصنيف النصوص غير المسبق. أخيرا، نعيد استخراج الكلمات الرئيسية من النصوص المبوبة. تظهر تجارب واسعة النطاق على كل من مجموعات البيانات الطويلة والنص القصير أن طريقتنا تتفوق بشكل كبير على تلك الموجودة.
Weakly-supervised text classification has received much attention in recent years for it can alleviate the heavy burden of annotating massive data. Among them, keyword-driven methods are the mainstream where user-provided keywords are exploited to generate pseudo-labels for unlabeled texts. However, existing methods treat keywords independently, thus ignore the correlation among them, which should be useful if properly exploited. In this paper, we propose a novel framework called ClassKG to explore keyword-keyword correlation on keyword graph by GNN. Our framework is an iterative process. In each iteration, we first construct a keyword graph, so the task of assigning pseudo labels is transformed to annotating keyword subgraphs. To improve the annotation quality, we introduce a self-supervised task to pretrain a subgraph annotator, and then finetune it. With the pseudo labels generated by the subgraph annotator, we then train a text classifier to classify the unlabeled texts. Finally, we re-extract keywords from the classified texts. Extensive experiments on both long-text and short-text datasets show that our method substantially outperforms the existing ones.
References used
https://aclanthology.org/
rate research
Read More
In cross-lingual text classification, it is required that task-specific training data in high-resource source languages are available, where the task is identical to that of a low-resource target language. However, collecting such training data can b
e infeasible because of the labeling cost, task characteristics, and privacy concerns. This paper proposes an alternative solution that uses only task-independent word embeddings of high-resource languages and bilingual dictionaries. First, we construct a dictionary-based heterogeneous graph (DHG) from bilingual dictionaries. This opens the possibility to use graph neural networks for cross-lingual transfer. The remaining challenge is the heterogeneity of DHG because multiple languages are considered. To address this challenge, we propose dictionary-based heterogeneous graph neural network (DHGNet) that effectively handles the heterogeneity of DHG by two-step aggregations, which are word-level and language-level aggregations. Experimental results demonstrate that our method outperforms pretrained models even though it does not access to large corpora. Furthermore, it can perform well even though dictionaries contain many incorrect translations. Its robustness allows the usage of a wider range of dictionaries such as an automatically constructed dictionary and crowdsourced dictionary, which are convenient for real-world applications.
Graph convolutional networks (GCNs) have been applied recently to text classification and produced an excellent performance. However, existing GCN-based methods do not assume an explicit latent semantic structure of documents, making learned represen
tations less effective and difficult to interpret. They are also transductive in nature, thus cannot handle out-of-graph documents. To address these issues, we propose a novel model named inductive Topic Variational Graph Auto-Encoder (T-VGAE), which incorporates a topic model into variational graph-auto-encoder (VGAE) to capture the hidden semantic information between documents and words. T-VGAE inherits the interpretability of the topic model and the efficient information propagation mechanism of VGAE. It learns probabilistic representations of words and documents by jointly encoding and reconstructing the global word-level graph and bipartite graphs of documents, where each document is considered individually and decoupled from the global correlation graph so as to enable inductive learning. Our experiments on several benchmark datasets show that our method outperforms the existing competitive models on supervised and semi-supervised text classification, as well as unsupervised text representation learning. In addition, it has higher interpretability and is able to deal with unseen documents.
Abstract Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this prob
lem, we propose SSL-Reg, a data-dependent regularization approach based on self-supervised learning (SSL). SSL (Devlin et al., 2019a) is an unsupervised learning approach that defines auxiliary tasks on input data without using any human-provided labels and learns data representations by solving these auxiliary tasks. In SSL-Reg, a supervised classification task and an unsupervised SSL task are performed simultaneously. The SSL task is unsupervised, which is defined purely on input texts without using any human- provided labels. Training a model using an SSL task can prevent the model from being overfitted to a limited number of class labels in the classification task. Experiments on 17 text classification datasets demonstrate the effectiveness of our proposed method. Code is available at https://github.com/UCSD-AI4H/SSReg.
Generating long text conditionally depending on the short input text has recently attracted more and more research efforts. Most existing approaches focus more on introducing extra knowledge to supplement the short input text, but ignore the coherenc
e issue of the generated texts. To address aforementioned research issue, this paper proposes a novel two-stage approach to generate coherent long text. Particularly, we first build a document-level path for each output text with each sentence embedding as its node, and a revised self-organising map (SOM) is proposed to cluster similar nodes of a family of document-level paths to construct the directed semantic graph. Then, three subgraph alignment methods are proposed to extract the maximum matching paths or subgraphs. These directed subgraphs are considered to well preserve extra but relevant content to the short input text, and then they are decoded by the employed pre-trained model to generate coherent long text. Extensive experiments have been performed on three real-world datasets, and the promising results demonstrate that the proposed approach is superior to the state-of-the-art approaches w.r.t. a number of evaluation criteria.
Short text classification is a fundamental task in natural language processing. It is hard due to the lack of context information and labeled data in practice. In this paper, we propose a new method called SHINE, which is based on graph neural networ
k (GNN), for short text classification. First, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs which introduce more semantic and syntactic information. Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts. Thus, comparing with existing GNN-based methods, SHINE can better exploit interactions between nodes of the same types and capture similarities between short texts. Extensive experiments on various benchmark short text datasets show that SHINE consistently outperforms state-of-the-art methods, especially with fewer labels.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
