Event Extraction by Answering (Almost) Natural Questions

By Xinya Du, Claire Cardie. Conference on Empirical Methods in Natural Language Processing, 2020

492 citations recorded by the source corpus.

The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments. Existing work in event argument extraction typically relies heavily on entity recognition as a preprocessing/concurrent step, causing the well-known problem of error propagation. To avoid this issue, we introduce a new paradigm for event extraction by formulating it as a question answering (QA) task, which extracts the event arguments in an end-to-end manner. Empirical results demonstrate that our framework outperforms prior methods substantially; in addition, it is capable of extracting event arguments for roles not seen at training time (zero-shot learning setting).

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/37e3ebc322895dd9348f080c45600dca737ff60f

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

1. Lifu Huang
2. Heng Ji
3. Mo Yu
4. Shiyu Chang
5. Yubo Chen
6. Sijia Wang
7. Kang Liu
8. Jiawei Han

Citations in the corpus

• Document-Level Event Argument Extraction by Conditional Generation (2021, methodology): “ularly used BERT-CRF baseline (Shi and Lin, 2019) that performs trigger extraction on sentencelevel and BERT-QA (Du and Cardie, 2020) ran on sentence-level and document-level.”
• Event Extraction as Machine Reading Comprehension (2020, methodology): “But different from our work, most of the above methods (Levy et al., 2017; Li et al., 2019b; FitzGerald et al., 2018; Du and Cardie, 2020) adopt human-designed, context-independent questions, which may not provide enough contextual evidence for question-answering.”
• Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021, methodology): “…a trigger-argument pipeline manner (Paolini et al., 2021); Multi-task TANL extends TANL by transferring structure knowledge from other tasks; EEQA (Du and Cardie, 2020) and MQAEE (Li et al., 2020) are QA-based models which use machine reading comprehension model for trigger detection and argument…”
• Summary of ChatGPT/GPT-4 Research and Perspective Towards the Future of Large Language Models (2023, methodology): “The results show that the average performance of Chat-GPT in long-tail and complex scenarios is only 51.04% of that of task-specific models such as EEQA.”
• Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models (2023, methodology): “Gao et al. [19] explored the feasibility and challenges of ChatGPT for event extraction on the ACE2005 corpus, evaluating the performance of ChatGPT in long-tail and complex scenarios (texts containing multiple events) and comparing it with two task-specific models, Text2Event and EEQA [57; 14].”
• Zero-Shot Information Extraction via Chatting with ChatGPT (2023, result): “For the ACE05 dataset, the predicted argument results are matched with the manually marked argument results at the entity level and evaluated by the micro F1.”
• Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2021, methodology): “Recent studies that model event extraction as question answering (Du and Cardie, 2020; Liu et al., 2020; Li et al., 2020) can take advantage of the semantics of event types and the large-scale question answering datasets.”
• 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.”