HMEAE: Hierarchical Modular Event Argument Extraction Xiaozhi Wang 1 - - PowerPoint PPT Presentation

▶

Mar 14, 2024 216 likes •427 views

Introduction Methodology Experiments HMEAE: Hierarchical Modular Event Argument Extraction Xiaozhi Wang 1 , Ziqi Wang 1 , Xu Han 1 , Zhiyuan Liu 1 , Juanzi Li 1 , Peng Li 2 , Maosong Sun 1 , Jie Zhou 2 , Xiang Ren 3 1 Department of Computer

SLIDE 1

Introduction Methodology Experiments

HMEAE: Hierarchical Modular Event Argument Extraction

Xiaozhi Wang1, Ziqi Wang1, Xu Han1, Zhiyuan Liu1, Juanzi Li1, Peng Li2, Maosong Sun1, Jie Zhou2, Xiang Ren3

1Department of Computer Science and Technology, Tsinghua University 2Pattern Recognition Center, WeChat, Tencent Inc 3Department of Computer Science, University of Southern California.

November 7, 2019

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 1 / 19

SLIDE 2

Introduction Methodology Experiments

Introduction

Event argument extraction (EAE):
Identify the entities serving as event arguments
Classify their argument roles
Second stage of Event Extraction

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 2 / 19

SLIDE 3

Introduction Methodology Experiments

Introduction

The second stage of Event Extraction
The bottleneck of Event Extraction

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 3 / 19

SLIDE 4

Introduction Methodology Experiments

Motivation

Existing methods treat argument roles as mutually

independent

Some argument roles are conceptually closer than others

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 4 / 19

SLIDE 5

Introduction Methodology Experiments

Motivation

Some argument roles are conceptually closer than others
How to utilize the concept hierarchy?

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 5 / 19

SLIDE 6

Introduction Methodology Experiments

Our Model

Neural Module Networks
Imitating the concept hierarchical structure
Provide effective inductive bias for EAE

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 6 / 19

SLIDE 7

Introduction Methodology Experiments

Overall architecture

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 7 / 19

SLIDE 8

Introduction Methodology Experiments

Superordinate Concept Module (SCM)

One superordinate concept is corresponding to one module
Attention module, to highlight related information

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 8 / 19

SLIDE 9

Introduction Methodology Experiments

Superordinate Concept Module (SCM)

One superordinate concept is corresponding to one module
Attention module, to highlight related information

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 9 / 19

SLIDE 10

Introduction Methodology Experiments

Logic Union Module

Compose corresponding SCMs
Depends on the argument role

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 10 / 19

SLIDE 11

Introduction Methodology Experiments

Argument Role Classifier

Given the embeddings
Predict whether this instance is of this argument role

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 11 / 19

SLIDE 12

Introduction Methodology Experiments

Instance Encoder

Encode text and the candidate entity into embeddings
Feature Aggregator: pooling, aggregate into a global instance

embedding

HMEAE is agnostic to the encoder

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 12 / 19

SLIDE 13

Introduction Methodology Experiments

Instance Encoder

Encode text and the candidate entity into embeddings
Feature Aggregator: pooling, aggregate into a global instance

embedding

HMEAE is agnostic to the encoder

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 13 / 19

SLIDE 14

Introduction Methodology Experiments

Instance Encoder

Encode text and the candidate entity into embeddings
Feature Aggregator: pooling, aggregate into a global instance

embedding

HMEAE is agnostic to the encoder

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 14 / 19

SLIDE 15

Introduction Methodology Experiments

Overall Results

Method Argument Role Classification P R F1 Li’s Joint 64.7 44.4 52.7 DMCNN 62.2 46.9 53.5 RBPB 54.1 53.5 53.8 JRNN 54.2 56.7 55.4 dbRNN 66.2 52.8 58.7 HMEAE (CNN) 57.3 54.2 55.7 DMBERT 58.8 55.8 57.2 HMEAE (BERT) 62.2 56.6 59.3

Table 1: The overall results (%) on ACE 2005.

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 15 / 19

SLIDE 16

Introduction Methodology Experiments

Overall Results

Method Argument Role Classification P R F1 DISCERN-R 7.9 7.4 7.7 Washington4 32.1 5.0 8.7 CMU CS Event1 31.2 4.9 8.4 Washington1 26.5 6.8 10.8 DMCNN 17.9 16.0 16.9 HMEAE (CNN) 15.3 22.5 18.2 DMBERT 22.6 24.7 23.6 HMEAE (BERT) 24.8 25.4 25.1

Table 2: The overall results (%) on TAC KBP 2016.

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 16 / 19

SLIDE 17

Introduction Methodology Experiments

Case Study

Do the SCMs really capture its corresponding concepts?

Person Org Time

Barry Diller

Wednesday quit as chief

Vivendi Universal Entertainment

0.15 0.30 0.45 0.60

Figure 1: Heatmap for attention scores of three SCMs on the left sentence.

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 17 / 19

SLIDE 18

Introduction Methodology Experiments

Conclusion and Future work

A modular architecture imitating a prior structure (concept

hierarchy) can provide effective inductive bias

Other tasks? Other priors?
Automatic design the architecture?

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 18 / 19

SLIDE 19

Introduction Methodology Experiments

The End

Thanks for listening. Questions are welcome.

(a) Code (b) Paper

Xiaozhi Wang HMEAE: Hierarchical Modular Event Argument Extraction 19 / 19