Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSynchronous Dual Network with Cross-Type Attention for Joint Entity and Relation Extraction
شبكة مزدوجة متزامنة مع الاهتمام عبر النوع من أجل كيان مشترك واستخراج العلاقات
347
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
إن كيان مشترك واستخراج العلاقات يمثل تحديا بسبب التفاعل المعقد للتفاعل بين التعرف على الكيان المسمى واستخراج العلاقة. على الرغم من أن معظم الأعمال القائمة تميل إلى تدريب هذه المهامتين المشتركين من خلال شبكة مشتركة، إلا أنها تفشل في الاستفادة الكاملة من الترابط بين أنواع الكيان وأنواع العلاقات. في هذه الورقة، نقوم بتصميم شبكة مزدوجة متزامنة رواية (SDN) مع اهتمام عبر النوع عبر الانتباه بشكل منفصل وتفاعي تفاعلي أنواع الكيان وأنواع العلاقات. من ناحية، يعتمد SDN اثنين من النوع BI اتجاهي ISOMORPHIC LSTM لترميز التمثيلات المحسنة نوع الكيان والتمثيلات المحسنة نوع العلاقة، على التوالي. من ناحية أخرى، نماذج SDN صراحة الترابط بين أنواع الكيان وأنواع العلاقات عبر آلية الاهتمام عبر النوع. بالإضافة إلى ذلك، نقترح أيضا استراتيجية تعليمية متعددة المهام الجديدة عبر النمذجة تفاعل نوعين من المعلومات. تجارب مجموعات بيانات NYT و WEBNLG تحقق من فعالية النموذج المقترح، وتحقيق الأداء الحديث في الفن.
Joint entity and relation extraction is challenging due to the complex interaction of interaction between named entity recognition and relation extraction. Although most existing works tend to jointly train these two tasks through a shared network, they fail to fully utilize the interdependence between entity types and relation types. In this paper, we design a novel synchronous dual network (SDN) with cross-type attention via separately and interactively considering the entity types and relation types. On the one hand, SDN adopts two isomorphic bi-directional type-attention LSTM to encode the entity type enhanced representations and the relation type enhanced representations, respectively. On the other hand, SDN explicitly models the interdependence between entity types and relation types via cross-type attention mechanism. In addition, we also propose a new multi-task learning strategy via modeling the interaction of two types of information. Experiments on NYT and WebNLG datasets verify the effectiveness of the proposed model, achieving state-of-the-art performance.
References used
https://aclanthology.org/
rate research
Read More
In joint entity and relation extraction, existing work either sequentially encode task-specific features, leading to an imbalance in inter-task feature interaction where features extracted later have no direct contact with those that come first. Or t
hey encode entity features and relation features in a parallel manner, meaning that feature representation learning for each task is largely independent of each other except for input sharing. We propose a partition filter network to model two-way interaction between tasks properly, where feature encoding is decomposed into two steps: partition and filter. In our encoder, we leverage two gates: entity and relation gate, to segment neurons into two task partitions and one shared partition. The shared partition represents inter-task information valuable to both tasks and is evenly shared across two tasks to ensure proper two-way interaction. The task partitions represent intra-task information and are formed through concerted efforts of both gates, making sure that encoding of task-specific features is dependent upon each other. Experiment results on six public datasets show that our model performs significantly better than previous approaches. In addition, contrary to what previous work has claimed, our auxiliary experiments suggest that relation prediction is contributory to named entity prediction in a non-negligible way. The source code can be found at https://github.com/Coopercoppers/PFN.
The way information is generated and disseminated has changed dramatically over the last decade. Identifying the political perspective shaping the way events are discussed in the media becomes more important due to the sharp increase in the number of
news outlets and articles. Previous approaches usually only leverage linguistic information. However, news articles attempt to maintain credibility and seem impartial. Therefore, bias is introduced in subtle ways, usually by emphasizing different aspects of the story. In this paper, we propose a novel framework that considers entities mentioned in news articles and external knowledge about them, capturing the bias with respect to those entities. We explore different ways to inject entity information into the text model. Experiments show that our proposed framework achieves significant improvements over the standard text models, and is capable of identifying the difference in news narratives with different perspectives.
Knowledge Graphs (KGs) have become increasingly popular in the recent years. However, as knowledge constantly grows and changes, it is inevitable to extend existing KGs with entities that emerged or became relevant to the scope of the KG after its cr
eation. Research on updating KGs typically relies on extracting named entities and relations from text. However, these approaches cannot infer entities or relations that were not explicitly stated. Alternatively, embedding models exploit implicit structural regularities to predict missing relations, but cannot predict missing entities. In this article, we introduce a novel method to enrich a KG with new entities given their textual description. Our method leverages joint embedding models, hence does not require entities or relations to be named explicitly. We show that our approach can identify new concepts in a document corpus and transfer them into the KG, and we find that the performance of our method improves substantially when extended with techniques from association rule mining, text mining, and active learning.
To alleviate label scarcity in Named Entity Recognition (NER) task, distantly supervised NER methods are widely applied to automatically label data and identify entities. Although the human effort is reduced, the generated incomplete and noisy annota
tions pose new challenges for learning effective neural models. In this paper, we propose a novel dictionary extension method which extracts new entities through the type expanded model. Moreover, we design a multi-granularity boundary-aware network which detects entity boundaries from both local and global perspectives. We conduct experiments on different types of datasets, the results show that our model outperforms previous state-of-the-art distantly supervised systems and even surpasses the supervised models.
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.
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
