https://github.com/zjunlp/doced

[ACL 2021] MLBiNet: A Cross-Sentence Collective Event Detection Network
https://github.com/zjunlp/doced

cross-sentence event-detection event-extraction

Last synced: about 1 month ago
JSON representation

[ACL 2021] MLBiNet: A Cross-Sentence Collective Event Detection Network

• Host: GitHub
• URL: https://github.com/zjunlp/doced
• Owner: zjunlp
• Created: 2021-04-04T13:35:31.000Z (about 5 years ago)
• Default Branch: main
• Last Pushed: 2022-01-10T06:19:46.000Z (about 4 years ago)
• Last Synced: 2026-01-31T23:21:36.786Z (2 months ago)
• Topics: cross-sentence, event-detection, event-extraction
• Language: Python
• Homepage:
• Size: 17.1 MB
• Stars: 35
• Watchers: 3
• Forks: 6
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Citation: CITATION.cff

Awesome Lists containing this project

README

          
# DocED

This repository is the official implementation of the ACL 2021 paper [MLBiNet: A Cross-Sentence Collective Event Detection Network](https://arxiv.org/pdf/2105.09458v1.pdf).

## Requirements

### To install basic requirements:

pip install requirements.txt

## Datasets

ACE2005 can be found here: https://catalog.ldc.upenn.edu/LDC2006T06

## Basic training

### To evaluate a setting with serveral random trials, execute

python run_experiments_multi.py

#### Main hyperparameters in train_MLBiNet.py include:

--tagging_mechanism,   mechanism to model event inter-dependency, you can choose one of "forward_decoder", "backward_decoder" or "bidirectional_decoder"

--num_tag_layers,   number of tagging layers, 1 indicates that we do sentence-level ED, 2 indicates that information of adjacent sentences were aggregated, ...

--max_doc_len,   maximum number of consecutive sentences are extracted as a mini-document, we can set it as 8 or 16

--tag_dim,   dimension of an uni-directional event tagging vector

--self_att_not,   whether to apply self-attention mechanism in sentence encoder 

## Main results

### Overall performance on ACE2005

![image](https://user-images.githubusercontent.com/32415352/118842889-252e6900-b8fc-11eb-9de8-dba5f82377f4.png)

### Performance on detecting multiple events collectively

![image](https://user-images.githubusercontent.com/32415352/118843522-b9003500-b8fc-11eb-8e3f-759f6d37f98a.png)

where 1/1 means one sentence that has one event; otherwise, 1/n is used.

### Performance of our proposed method with different multi-layer settings or decoder methods

![image](https://user-images.githubusercontent.com/32415352/118843910-11cfcd80-b8fd-11eb-965c-fbcde1319983.png)

## How to Cite

```bibtex

@inproceedings{ACL2021_MLBiNet,

  author    = {Dongfang Lou and

               Zhilin Liao and

               Shumin Deng and

               Ningyu Zhang and

               Huajun Chen},

  title     = {MLBiNet: A Cross-Sentence Collective Event Detection Network},

  booktitle = {{ACL}},

  publisher = {Association for Computational Linguistics},

  year      = {2021}

}

```