DCFEE: A Document-level Chinese Financial Event Extraction System based on Automatically Labeled Training Data

  title={DCFEE: A Document-level Chinese Financial Event Extraction System based on Automatically Labeled Training Data},
  author={Hang Yang and Yubo Chen and Kang Liu and Yang Xiao and Jun Zhao},
We present an event extraction framework to detect event mentions and extract events from the document-level financial news. [] Key Method To solve these problems, we propose a Document-level Chinese Financial Event Extraction (DCFEE) system which can automatically generate a large scaled labeled data and extract events from the whole document. Experimental results demonstrate the effectiveness of it.

Figures and Tables from this paper

FEED: A Chinese Financial Event Extraction Dataset Constructed by Distant Supervision
A large-scale Chinese financial event extraction dataset FEED is released, consisting of 31,748 documents on five financial event types derived from the Chinese financial portals, which considers the case of event arguments scattered in multiple sentences and one document containing multiple events.
A Prior Information Enhanced Extraction Framework for Document-level Financial Event Extraction
A novel Prior Information Enhanced Extraction framework for DFEE, leveraging prior information from both event types and pre-trained language models is proposed, which takes the first place and significantly outperforms the other systems.
Doc2EDAG: An End-to-End Document-level Framework for Chinese Financial Event Extraction
This work proposes a novel end-to-end model, Doc2EDAG, which can generate an entity-based directed acyclic graph to fulfill the document-level EE (DEE) effectively and reformalizes a DEE task with the no-trigger-words design to ease the documents-level event labeling.
Knowledge Graph Enhanced Event Extraction in Financial Documents
This work proposes a first event extraction framework that embeds a knowledge graph through a Graph Neural Network and integrates the embedding with regular features, all at document-level, and demonstrates its effectiveness in improving the performance of multiple events extraction.
Probing into the Root: A Dataset for Reason Extraction of Structural Events from Financial Documents
This paper proposes a new task regarding event reason extraction from document-level texts, which does not assign target events in the text, but only provide structural event descriptions, and such settings accord more with practice scenarios.
Document-level Core Events Extraction based on QA
Document-level core events extraction model based on QA is provided and the experimental results on ACE2005 Chinese corpus show that the event argument role question with prior information has a good effect on event argument extraction.
ALGA: Automatic Logic Gate Annotator for Building Financial News Events Detectors
It is shown that event detection classifiers trained on the data generated by the ALGA framework can achieve state-of-the-art performance in the domain-speciflc financial events detection task.
Exploring Pre-trained Language Models for Event Extraction and Generation
This work proposes an event extraction model to overcome the roles overlap problem by separating the argument prediction in terms of roles, and proposes a method to automatically generate labeled data by editing prototypes and screen out generated samples by ranking the quality.
Event Extraction via DMCNN in Open Domain Public Sentiment Information
Experiments show that structured information can be extracted from unstructured text, and the purpose of obtaining public opinion event entities, event-entity relationships, and entity attribute information can been achieved.
Chinese medical event detection based on feature extension and document consistency
  • Chen Wang, Pengjun Zhai, Yu Fang
  • Computer Science
    2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE)
  • 2020
This paper proposes an event detection method based on feature extension and document consistency that is significantly superior to the baseline and uses semiautomatic corpus labeling method to label entities and events.


Automatically Labeled Data Generation for Large Scale Event Extraction
This work proposes to automatically label training data for event extraction via world knowledge and linguistic knowledge, which can detect key arguments and trigger words for each event type and employ them to label events in texts automatically.
Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks
A word-representation model to capture meaningful semantic regularities for words and a framework based on a convolutional neural network to capture sentence-level clues are introduced.
Refining Event Extraction through Cross-Document Inference
This work designs a simple scheme to conduct cross-document inference for improving the ACE event extraction task, and applies the hypothesis of “One Sense Per Discourse” to information extraction.
Multi-Event Extraction Guided by Global Constraints
This paper aims to identify the fields of information contained in a document and aggregate together those fields that describe the same event, and proposes a novel model that substantially outperforms traditional pipeline models.
Enhanced Services for Targeted Information Retrieval by Event Extraction and Data Mining
We present a framework combining information retrieval with machine learning and (pre-)processing for named entity recognition in order to extract events from a large document collection. The
Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks
This paper proposes a novel model dubbed the Piecewise Convolutional Neural Networks (PCNNs) with multi-instance learning to address the problem of wrong label problem when using distant supervision for relation extraction and adopts convolutional architecture with piecewise max pooling to automatically learn relevant features.
Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms
This work systematically investigates the proposed model under the supervision of different attention strategies and shows that the approach advances state-of-the-arts and achieves the best F1 score on ACE 2005 dataset.
Incorporating Copying Mechanism in Sequence-to-Sequence Learning
This paper incorporates copying into neural network-based Seq2Seq learning and proposes a new model called CopyNet with encoder-decoder structure which can nicely integrate the regular way of word generation in the decoder with the new copying mechanism which can choose sub-sequences in the input sequence and put them at proper places in the output sequence.
The stages of event extraction
This paper presents a simple, modular approach to event extraction that allows for experiment with a variety of machine learning methods for sub-tasks of varying difficulty, as well as to evaluate the impact on performance these sub-Tasks have on the overall task.