# CUP: Curriculum Learning based Prompt Tuning for Implicit Event Argument Extraction

arXiv: https://arxiv.org/abs/2205.00498 · HTML: https://mlsanity.com/paper/2205.00498/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 1 May 2022.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020)
- [Document-Level Event Argument Extraction by Conditional Generation](https://mlsanity.com/paper/2104.05919/) (2021)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [Entity-Relation Extraction as Multi-Turn Question Answering](https://mlsanity.com/paper/1905.05529/) (2019)
- [Multi-Sentence Argument Linking](https://mlsanity.com/paper/1911.03766/) (2019)
- [Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation](https://mlsanity.com/paper/1809.09078/) (2018)
- [Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding](https://mlsanity.com/paper/2005.06579/) (2020)
- [AMR Parsing with Action-Pointer Transformer](https://mlsanity.com/paper/2104.14674/) (2021)
- [Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder](https://mlsanity.com/paper/2107.00189/) (2021)
- [Reporting the Unreported: Event Extraction for Analyzing the Local Representation of Hate Crimes](https://mlsanity.com/paper/1909.02126/) (2019)
- [GRIT: Generative Role-filler Transformers for Document-level Event Entity Extraction](https://mlsanity.com/paper/2008.09249/) (2020)

## Built on by (most cited first, 7 of 7)

- [A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck](https://mlsanity.com/paper/2208.13017/) (2022)
- [An AMR-based Link Prediction Approach for Document-level Event Argument Extraction](https://mlsanity.com/paper/2305.19162/) (2023)
- [A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction](https://mlsanity.com/paper/2403.09721/) (2024)
- [Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments](https://mlsanity.com/paper/2312.03726/) (2023)
- [Curriculum Design Helps Spiking Neural Networks to Classify Time Series](https://mlsanity.com/paper/2401.10257/) (2023)
- [Causal Intervention-based Prompt Debiasing for Event Argument Extraction](https://mlsanity.com/paper/2210.01561/) (2022)
- [Token-Event-Role Structure-based Multi-Channel Document-Level Event Extraction](https://mlsanity.com/paper/2306.17733/) (2023)

## Abstract (arXiv)

Implicit event argument extraction (EAE) aims to identify arguments that could scatter over the document. Most previous work focuses on learning the direct relations between arguments and the given trigger, while the implicit relations with long-range dependency are not well studied. Moreover, recent neural network based approaches rely on a large amount of labeled data for training, which is unavailable due to the high labelling cost. In this paper, we propose a Curriculum learning based Prompt tuning (CUP) approach, which resolves implicit EAE by four learning stages. The stages are defined according to the relations with the trigger node in a semantic graph, which well captures the long-range dependency between arguments and the trigger. In addition, we integrate a prompt-based encoder-decoder model to elicit related knowledge from pre-trained language models (PLMs) in each stage, where the prompt templates are adapted with the learning progress to enhance the reasoning for arguments. Experimental results on two well-known benchmark datasets show the great advantages of our proposed approach. In particular, we outperform the state-of-the-art models in both fully-supervised and low-data scenarios.