Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Partition Filter Network for Joint Entity and Relation Extraction
شبكة تصفية القسم لاستخراج الكيان المشترك والعلاقة
349
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في استخراج الكيان المشترك والعلاقة، العمل الحالي إما ترميز الميزات الخاصة بمهام المهام بالتتابع، مما يؤدي إلى عدم التوازن في تفاعل الميزات المشتركة بين المهام حيث لا يكون للميزات المستخرجة لاحقا اتصالا مباشرا مع تلك التي تأتي أولا. أو ترميز ميزات الكيان وميزات العلاقة بطريقة متوازية، مما يعني أن التعلم التمثيل الميزات لكل مهمة مستقلة إلى حد كبير عن بعضها البعض باستثناء مشاركة الإدخال. نقترح شبكة تصفية القسم لنموذج التفاعل في اتجاهين بين المهام بشكل صحيح، حيث تحلل ترميز الميزة في خطوتين: القسم والتصفية. في تشفيرنا، نحن نستفيد بوابات اثنين: كيان وبوابة العلاقة، إلى الخلايا العصبية بالقطاع إلى قسمين مهمتين وتقسيم مشترك واحد. يمثل القسم المشترك معلومات مشتركة بين المهام القيمة لكل من المهام ويتم تقاسمها بالتساوي عبر مهمتين لضمان التفاعل السليم في اتجاهين. تمثل أقسام المهام معلومات مهمة داخلية ويتم تشكيلها من خلال الجهود المتضاحية لكل من البوابات، مما يتأكد من أن ترميز ميزات المهام الخاصة يعتمد على بعضها البعض. تظهر نتائج التجربة على ستة مجموعات بيانات عامة أن طرازنا يؤدي أفضل بكثير من النهج السابقة. بالإضافة إلى ذلك، على عكس ما ادعى العمل السابق، تشير تجاربنا الإضافية إلى أن التنبؤ بالعلامة مساهمة في تنبؤ الكيان المسمى بطريقة غير مهم. يمكن العثور على شفرة المصدر في https://github.com/coopercoper/pfn.
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 they 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.
References used
https://aclanthology.org/
rate research
Read More
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, t
hey 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.
Nested Named Entity Recognition (NNER) has been extensively studied, aiming to identify all nested entities from potential spans (i.e., one or more continuous tokens). However, recent studies for NNER either focus on tedious tagging schemas or utiliz
e complex structures, which fail to learn effective span representations from the input sentence with highly nested entities. Intuitively, explicit span representations will contribute to NNER due to the rich context information they contain. In this study, we propose a Hierarchical Transformer (HiTRANS) network for the NNER task, which decomposes the input sentence into multi-grained spans and enhances the representation learning in a hierarchical manner. Specifically, we first utilize a two-phase module to generate span representations by aggregating context information based on a bottom-up and top-down transformer network. Then a label prediction layer is designed to recognize nested entities hierarchically, which naturally explores semantic dependencies among different spans. Experiments on GENIA, ACE-2004, ACE-2005 and NNE datasets demonstrate that our proposed method achieves much better performance than the state-of-the-art approaches.
Recent information extraction approaches have relied on training deep neural models. However, such models can easily overfit noisy labels and suffer from performance degradation. While it is very costly to filter noisy labels in large learning resour
ces, recent studies show that such labels take more training steps to be memorized and are more frequently forgotten than clean labels, therefore are identifiable in training. Motivated by such properties, we propose a simple co-regularization framework for entity-centric information extraction, which consists of several neural models with identical structures but different parameter initialization. These models are jointly optimized with the task-specific losses and are regularized to generate similar predictions based on an agreement loss, which prevents overfitting on noisy labels. Extensive experiments on two widely used but noisy benchmarks for information extraction, TACRED and CoNLL03, demonstrate the effectiveness of our framework. We release our code to the community for future research.
This paper studies the problem of cross-document event coreference resolution (CDECR) that seeks to determine if event mentions across multiple documents refer to the same real-world events. Prior work has demonstrated the benefits of the predicate-a
rgument information and document context for resolving the coreference of event mentions. However, such information has not been captured effectively in prior work for CDECR. To address these limitations, we propose a novel deep learning model for CDECR that introduces hierarchical graph convolutional neural networks (GCN) to jointly resolve entity and event mentions. As such, sentence-level GCNs enable the encoding of important context words for event mentions and their arguments while the document-level GCN leverages the interaction structures of event mentions and arguments to compute document representations to perform CDECR. Extensive experiments are conducted to demonstrate the effectiveness of the proposed model.
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.
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
