Cross-document event extraction and tracking: Task, evaluation, techniques and challenges

Heng Ji; Ralph Grishman; Zheng Chen; Prashant Gupta

Cross-document event extraction and tracking: Task, evaluation, techniques and challenges

Heng Ji, Ralph Grishman, Zheng Chen, Prashant Gupta

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper proposes a new task of cross-document event extraction and tracking and its evaluation metrics. We identify important person entities which are frequently involved in events as 'centroid entities'. Then we link the events involving the same centroid entity along a time line. We also present a system performing this task and our current approaches to address the main research challenges. We demonstrate that global inference from background knowledge and cross-document event aggregation are crucial to enhance the performance. This new task defines several extensions to the traditional single-document Information Extraction paradigm beyond 'slot filling'.

Original language	English (US)
Title of host publication	International Conference Recent Advances in Natural Language Processing, RANLP
Pages	166-172
Number of pages	7
State	Published - 2009
Event	International Conference on Recent Advances in Natural Language Processing, RANLP-2009 - Borovets, Bulgaria Duration: Sep 14 2009 → Sep 16 2009

Other

Other	International Conference on Recent Advances in Natural Language Processing, RANLP-2009
Country/Territory	Bulgaria
City	Borovets
Period	9/14/09 → 9/16/09

Keywords

Cross-document extraction
Event
Information extraction

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Software
Electrical and Electronic Engineering

Cite this

@inproceedings{7f6cb9a04be642da8f854b19e257595c,

title = "Cross-document event extraction and tracking: Task, evaluation, techniques and challenges",

abstract = "This paper proposes a new task of cross-document event extraction and tracking and its evaluation metrics. We identify important person entities which are frequently involved in events as 'centroid entities'. Then we link the events involving the same centroid entity along a time line. We also present a system performing this task and our current approaches to address the main research challenges. We demonstrate that global inference from background knowledge and cross-document event aggregation are crucial to enhance the performance. This new task defines several extensions to the traditional single-document Information Extraction paradigm beyond 'slot filling'.",

keywords = "Cross-document extraction, Event, Information extraction",

author = "Heng Ji and Ralph Grishman and Zheng Chen and Prashant Gupta",

year = "2009",

language = "English (US)",

pages = "166--172",

booktitle = "International Conference Recent Advances in Natural Language Processing, RANLP",

note = "International Conference on Recent Advances in Natural Language Processing, RANLP-2009 ; Conference date: 14-09-2009 Through 16-09-2009",

}

TY - GEN

T1 - Cross-document event extraction and tracking

T2 - International Conference on Recent Advances in Natural Language Processing, RANLP-2009

AU - Ji, Heng

AU - Grishman, Ralph

AU - Chen, Zheng

AU - Gupta, Prashant

PY - 2009

Y1 - 2009

N2 - This paper proposes a new task of cross-document event extraction and tracking and its evaluation metrics. We identify important person entities which are frequently involved in events as 'centroid entities'. Then we link the events involving the same centroid entity along a time line. We also present a system performing this task and our current approaches to address the main research challenges. We demonstrate that global inference from background knowledge and cross-document event aggregation are crucial to enhance the performance. This new task defines several extensions to the traditional single-document Information Extraction paradigm beyond 'slot filling'.

AB - This paper proposes a new task of cross-document event extraction and tracking and its evaluation metrics. We identify important person entities which are frequently involved in events as 'centroid entities'. Then we link the events involving the same centroid entity along a time line. We also present a system performing this task and our current approaches to address the main research challenges. We demonstrate that global inference from background knowledge and cross-document event aggregation are crucial to enhance the performance. This new task defines several extensions to the traditional single-document Information Extraction paradigm beyond 'slot filling'.

KW - Cross-document extraction

KW - Event

KW - Information extraction

UR - http://www.scopus.com/inward/record.url?scp=84866851168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866851168&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84866851168

SP - 166

EP - 172

BT - International Conference Recent Advances in Natural Language Processing, RANLP

Y2 - 14 September 2009 through 16 September 2009

ER -

Cross-document event extraction and tracking: Task, evaluation, techniques and challenges

Abstract

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this