Joint Event Extraction via Structured Prediction with Global Features

By Qi Li, Heng Ji, Liang Huang. 2013

587 citations recorded by the source corpus.

How researchers see this paper

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

1. Mohit Bansal
2. Mo Yu
3. Xu Han
4. Zhiyuan Liu
5. Yoav Goldberg
6. Thien Huu Nguyen
7. Kyunghyun Cho
8. Percy Liang

Citations in the corpus

• Using Structured Events to Predict Stock Price Movement: An Empirical Investigation (2014, neutral): “However, structured event extraction can be a costly task, requiring predefined event types and manual event templates (Ji and Gr-ishman, 2008; Li et al., 2013).”
• Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging (2017, methodology): “We use the same data split as Li et al. (2013). For the Event Detection task, we use the TempEval3 Task B setup.”
• A language-independent neural network for event detection (2016, methodology): “Table 3 shows the comparison results between our model and the state-of-the-art methods (Li et al., 2013; Chen et al., 2012).”
• Event Detection and Co-reference with Minimal Supervision (2016, background): “Li et al. (2013) presented a structured perceptron model to detect triggers and arguments jointly.”
• Context-Aware Representations for Knowledge Base Relation Extraction (2017, background): “Finally, Li et al. (2013) have designed global features and constraints to extract multiple events and their arguments from the same sentence.”
• Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021, unknown): “…Lin et al., 2018; Yang et al., 2019; Wang et al., 2019; Ma et al., 2020; Zhang et al., 2020c), 2) multi-task joint models (McClosky et al., 2011; Li et al., 2013, 2014; Yang and Mitchell, 2016; Nguyen et al., 2016; Liu et al., 2018; Zhang et al., 2019a; Zheng et al., 2019), 3) semantic…”
• Joint Event Extraction via Recurrent Neural Networks (2016, methodology): “Guided by these characteristics of the EE systems by Li et al. (2013) and Chen et al. (2015), in this work, we propose to solve the EE problem with the joint approach via recurrent neural networks (RNNs) (Hochreiter and Schmidhuber, 1997; Cho et al., 2014) augmented with the discrete features, thus…”
• Leveraging Knowledge Bases in LSTMs for Improving Machine Reading (2017, methodology): “We use the same data split and experimental setting as in Li et al. (2013).”
• Entity, Relation, and Event Extraction with Contextualized Span Representations (2019, methodology): “…previous works have used pipelines to extract syntactic, discourse, and other hand-engineered features as inputs to structured prediction models (Li et al., 2013; Yang and Mitchell, 2016; Li and Ji, 2014) and neural scoring functions (Nguyen and Nguyen, 2019), or as a guide for the construction…”
• Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms (2017, methodology): “lowed the evaluation of (Li et al., 2013; Chen et al., 2015; Liu et al., 2016b): randomly selected 30 articles from different genres as the development set, and subsequently conducted a blind test on a separate set of 40 ACE 2005 newswire documents.”
• Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2021, methodology): “We use Spacy 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 Detection and Domain Adaptation with Convolutional Neural Networks (2015, methodology): “Although this approach has achieved the top performance (Hong et al., 2011; Li et al., 2013b), it suffers from at least two issues: (i) The choice of features is a manual process and requires linguistic intuition as well as domain expertise, implying additional studies for new application domains…”
• Incremental Joint Extraction of Entity Mentions and Relations (2014, methodology): “Our previous work (Li et al., 2013) used structured perceptron with token-based decoder to jointly predict event triggers and arguments based on the assumption that entity mentions and other argument candidates are given as part of the input.”
• Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks (2015, methodology): “For comparison, as the same as Li et al. (2013), Hong et al. (2011) and Liao and Grishman (2010), we used the same test set with 40 newswire articles and the same development set with 30 other documents randomly selected from different genres and the rest 529 documents are used for training.”
• The Art of Prompting: Event Detection based on Type Specific Prompts (2022, methodology): “For SED, we use the same data split as the previous studies (Li et al., 2013; Wadden et al., 2019; Lin et al., 2020; Du and Cardie, 2020; Lin et al., 2020; Nguyen et al., 2021; Wang et al., 2020a) on all the three benchmark datasets.”
• Exploring Pre-trained Language Models for Event Extraction and Generation (2019, methodology): “As previous works (Li et al., 2013b; Chen et al., 2015; Hong et al., 2011), we take the test set with 40 newswire documents, while 30 other documents as the validation set, and the remaining 529 documents to be the training set.”
• Seed-Based Event Trigger Labeling: How far can event descriptions get us? (2015, methodology): “Therefore, we implemented our system by adapting the state-of-the-art fully-supervised event extraction system of Li et al. (2013), modifying mechanisms relevant for features and for trigger labels, as described below.”