Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks

By Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng, Jun Zhao. 2015

894 citations recorded by the source corpus.

Traditional approaches to the task of ACE event extraction primarily rely on elaborately designed features and complicated natural language processing (NLP) tools. These traditional approaches lack generalization, take a large amount of human effort and are prone to error propagation and data sparsity problems. This paper proposes a novel event-extraction method, which aims to automatically extract lexical-level and sentence-level features without using complicated NLP tools. We introduce a word-representation model to capture meaningful semantic regularities for words and adopt a framework based on a convolutional neural network (CNN) to capture sentence-level clues. However, CNN can only capture the most important information in a sentence and may miss valuable facts when considering multiple-event sentences. We propose a dynamic multi-pooling convolutional neural network (DMCNN), which uses a dynamic multi-pooling layer according to event triggers and arguments, to reserve more crucial information. The experimental results show that our approach significantly outperforms other state-of-the-art methods.

Subfields: Artificial Intelligence, Information Systems and Management, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems and Management

In Management Science and Operations Research

Citations in the corpus

A Primer on Neural Network Models for Natural Language Processing (2015, background): “We could argue that the words before the first word, the words after the second word, and the words between them provide three different kinds of information (Chen et al., 2015).”
Semi-supervised New Event Type Induction and Event Detection (2020, background): “Traditional event extraction studies (Ji and Grishman, 2008; McClosky et al., 2011; Li et al., 2013; Chen et al., 2015; Yang and Mitchell, 2016; Feng 5https://scikit-learn.org/stable/modules/ generated/sklearn.manifold.TSNE.html et al., 2016; Liu et al., 2018; Nguyen and Nguyen, 2019; Lin et al.,…”
Improving Event Extraction via Multimodal Integration (2017, background): “A number of EE models have brought forth encouraging results by retrieving additional related text documents [19, 22, 37], extracting salient textual features [15, 24, 26], and adopting more advanced learning frameworks [5, 7, 16, 29].”
Event Detection and Co-reference with Minimal Supervision (2016, methodology): “We select 40 documents from newswire articles for event detection evaluation and the rest for training (same as Chen et al. (2015)).”
Simplify the Usage of Lexicon in Chinese NER (2019, background): “NER plays an important role in many downstream tasks, including knowledge base construction (Riedel et al., 2013), information retrieval (Chen et al., 2015), and question answering (Diefenbach et al., 2018).”
Lifelong Event Detection with Knowledge Transfer (2021, methodology): “…loss is used to train the model on the current dataset: Although some of the methods designed explicitly for event detection (Ji and Grishman, 2008; Chen et al., 2015; Feng et al., 2016; Liu et al., 2017; Yan et al., 2019; Tong et al., 2020) may have better detection performance, this model is…”
Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021, methodology): “…divided into: 1) pipeline classiﬁcation (Ahn, 2006; Ji and Grishman, 2008; Liao and Grishman, 2010; Hong et al., 2011, 2018; Huang and Riloff, 2012; Chen et al., 2015; Sha et al., 2016; Lin et al., 2018; Yang et al., 2019; Wang et al., 2019; Ma et al., 2020; Zhang et al., 2020c), 2) multi-task…”
Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2021, methodology): “…to862 generate POS tags.863 Evaluation Criteria For evaluation of super-864 vised event extraction, we use the same criteria865 as (Li et al., 2013; Chen et al., 2015; Nguyen et al.,866 2016; Lin et al., 2020) as follows:867 • Trigger: A trigger mention is correct if its 868 span and event type…”
Dual-path Convolutional Image-Text Embeddings with Instance Loss (2017, background): “There are also researchers who apply layer-by-layer CNNs for efficient text analysis [39]–[42], obtaining competitive results in title recognition, event detection and text content matching.”
Exploiting the Ground-Truth: An Adversarial Imitation Based Knowledge Distillation Approach for Event Detection (2019, methodology): “Representation-based approaches include (Chen et al. 2015; Nguyen and Grishman 2015) that used Convo-lution Neural Networks to do automatic feature engineering; (Feng et al. 2016) that leveraged hybrid networks for feature learning; (Nguyen, Cho, and Grishman 2016) that modeled non-continue…”
Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms (2017, methodology): “Representation-based methods typically represent candidate event mentions by embeddings and feed them into neural networks (Chen et al., 2015; Nguyen and Grishman, 2015; Liu et al., 2016a; Nguyen and Grishman, 2016).”
Graph Convolutional Networks With Argument-Aware Pooling for Event Detection (2018, methodology): “Specifically, we repeat the model selection procedure in Table 1 of the previous section to select the best network architecture for each pooling method of comparison in {ANCHOR, OVERALL, DYNAMIC} (using the ACE 2005 development dataset).”
Leveraging Knowledge Bases in LSTMs for Improving Machine Reading (2017, neutral): “…and global features (Li et al., 2013); J OINT E NTI - TY E VENT refers to the graphical model for joint entity and event extraction (Yang and Mitchell, 2016); DMCNN is the dynamic multi-pooling CNNs in Chen et al. (2015); and JRNN is an RNN model with memory introduced by Nguyen et al. (2016).”
Natural Language Processing Advancements By Deep Learning: A Survey (2020, methodology): “Convolutional neural networks have been utilized for event detection; they handle problems with feature-based approaches including exhaustive feature engineering and error propagation phenomena for feature generation [116].”