Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBeyond Text: Incorporating Metadata and Label Structure for Multi-Label Document Classification using Heterogeneous Graphs
ما بعد النص: دمج البيانات الوصفية والملصقات لتصنيف المستندات متعددة الملصقات باستخدام الرسوم البيانية غير المتجانسة
274
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يتم جذب تصنيف المستندات متعددة الملصقات، وربط مثيل مستندات واحدة بمجموعة من الملصقات ذات الصلة، المزيد والمزيد من اهتمام البحوث. استكشاف الأساليب الحالية دمج المعلومات وراء النص، مثل بيانات تعريف الوثيقة أو هيكل الملصقات. ومع ذلك، فإن هذه الأساليب إما ببساطة الاستفادة من المعلومات الدلالية من البيانات الوصفية أو توظيف التسلسل الهرمي لملصق الوالدين والطفل المحدد مسبقا، وتجاهل الهياكل الرسومية غير المتجانسة للبيانات الوصفية والملصقات، والتي نعتقد أنها حاسمة لتصنيف مستندات دقيقة متعددة الملصقات. لذلك، في هذه الورقة، نقترح نهجا جديدا في الشبكة العصبية لتصنيف المستندات متعددة الملصقات، حيث يتم بناء الرسوم البيانية غير المتجانسة والتعلم باستخدام محولات الرسم البياني غير المتجانس. أحدهما هو الرسم البياني غير المتجانس في البيانات الأولية، والتي نماذج أنواع مختلفة من البيانات الوصفية وعلاقاتها الطوبولوجية. الآخر هو الرسم البياني الملصق غير المتجانس، الذي تم إنشاؤه بناء على كل من التسلسل الهرمي للملصقات والتمثيل الإحصائي. النتائج التجريبية على مجموعة من مجموعات البيانات القياسية تظهر النهج المقترح تفوق العديد من خطوط الأساس الحديثة.
Multi-label document classification, associating one document instance with a set of relevant labels, is attracting more and more research attention. Existing methods explore the incorporation of information beyond text, such as document metadata or label structure. These approaches however either simply utilize the semantic information of metadata or employ the predefined parent-child label hierarchy, ignoring the heterogeneous graphical structures of metadata and labels, which we believe are crucial for accurate multi-label document classification. Therefore, in this paper, we propose a novel neural network based approach for multi-label document classification, in which two heterogeneous graphs are constructed and learned using heterogeneous graph transformers. One is metadata heterogeneous graph, which models various types of metadata and their topological relations. The other is label heterogeneous graph, which is constructed based on both the labels' hierarchy and their statistical dependencies. Experimental results on two benchmark datasets show the proposed approach outperforms several state-of-the-art baselines.
References used
https://aclanthology.org/
rate research
Read More
Multi-label document classification (MLDC) problems can be challenging, especially for long documents with a large label set and a long-tail distribution over labels. In this paper, we present an effective convolutional attention network for the MLDC
problem with a focus on medical code prediction from clinical documents. Our innovations are three-fold: (1) we utilize a deep convolution-based encoder with the squeeze-and-excitation networks and residual networks to aggregate the information across the document and learn meaningful document representations that cover different ranges of texts; (2) we explore multi-layer and sum-pooling attention to extract the most informative features from these multi-scale representations; (3) we combine binary cross entropy loss and focal loss to improve performance for rare labels. We focus our evaluation study on MIMIC-III, a widely used dataset in the medical domain. Our models outperform prior work on medical coding and achieve new state-of-the-art results on multiple metrics. We also demonstrate the language independent nature of our approach by applying it to two non-English datasets. Our model outperforms prior best model and a multilingual Transformer model by a substantial margin.
Exploiting label hierarchies has become a promising approach to tackling the zero-shot multi-label text classification (ZS-MTC) problem. Conventional methods aim to learn a matching model between text and labels, using a graph encoder to incorporate
label hierarchies to obtain effective label representations (Rios and Kavuluru, 2018). More recently, pretrained models like BERT (Devlin et al., 2018) have been used to convert classification tasks into a textual entailment task (Yin et al., 2019). This approach is naturally suitable for the ZS-MTC task. However, pretrained models are underexplored in the existing work because they do not generate individual vector representations for text or labels, making it unintuitive to combine them with conventional graph encoding methods. In this paper, we explore to improve pretrained models with label hierarchies on the ZS-MTC task. We propose a Reinforced Label Hierarchy Reasoning (RLHR) approach to encourage interdependence among labels in the hierarchies during training. Meanwhile, to overcome the weakness of flat predictions, we design a rollback algorithm that can remove logical errors from predictions during inference. Experimental results on three real-life datasets show that our approach achieves better performance and outperforms previous non-pretrained methods on the ZS-MTC task.
Hierarchical multi-label text classification (HMTC) deals with the challenging task where an instance can be assigned to multiple hierarchically structured categories at the same time. The majority of prior studies either focus on reducing the HMTC t
ask into a flat multi-label problem ignoring the vertical category correlations or exploiting the dependencies across different hierarchical levels without considering the horizontal correlations among categories at the same level, which inevitably leads to fundamental information loss. In this paper, we propose a novel HMTC framework that considers both vertical and horizontal category correlations. Specifically, we first design a loosely coupled graph convolutional neural network as the representation extractor to obtain representations for words, documents, and, more importantly, level-wise representations for categories, which are not considered in previous works. Then, the learned category representations are adopted to capture the vertical dependencies among levels of category hierarchy and model the horizontal correlations. Finally, based on the document embeddings and category embeddings, we design a hybrid algorithm to predict the categories of the entire hierarchical structure. Extensive experiments conducted on real-world HMTC datasets validate the effectiveness of the proposed framework with significant improvements over the baselines.
We introduce MULTI-EURLEX, a new multilingual dataset for topic classification of legal documents. The dataset comprises 65k European Union (EU) laws, officially translated in 23 languages, annotated with multiple labels from the EUROVOC taxonomy. We
highlight the effect of temporal concept drift and the importance of chronological, instead of random splits. We use the dataset as a testbed for zero-shot cross-lingual transfer, where we exploit annotated training documents in one language (source) to classify documents in another language (target). We find that fine-tuning a multilingually pretrained model (XLM-ROBERTA, MT5) in a single source language leads to catastrophic forgetting of multilingual knowledge and, consequently, poor zero-shot transfer to other languages. Adaptation strategies, namely partial fine-tuning, adapters, BITFIT, LNFIT, originally proposed to accelerate fine-tuning for new end-tasks, help retain multilingual knowledge from pretraining, substantially improving zero-shot cross-lingual transfer, but their impact also depends on the pretrained model used and the size of the label set.
This paper presents an efficient graph-enhanced approach to multi-document summarization (MDS) with an encoder-decoder Transformer model. This model is based on recent advances in pre-training both encoder and decoder on very large text data (Lewis e
t al., 2019), and it incorporates an efficient encoding mechanism (Beltagy et al., 2020) that avoids the quadratic memory growth typical for traditional Transformers. We show that this powerful combination not only scales to large input documents commonly found when summarizing news clusters; it also enables us to process additional input in the form of auxiliary graph representations, which we derive from the multi-document clusters. We present a mechanism to incorporate such graph information into the encoder-decoder model that was pre-trained on text only. Our approach leads to significant improvements on the Multi-News dataset, overall leading to an average 1.8 ROUGE score improvement over previous work (Li et al., 2020). We also show improvements in a transfer-only setup on the DUC-2004 dataset. The graph encodings lead to summaries that are more abstractive. Human evaluation shows that they are also more informative and factually more consistent with their input documents.
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
