Fine-grained semantic conceptualization of frameNet

Jin Woo Park, Seungwon Hwang, Haixun Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Understanding verbs is essential for many natural language tasks. To this end, large-scale lexical resources such as FrameNet have been manually constructed to annotate the semantics of verbs (frames) and their arguments (frame elements or FEs) in example sentences. Our goal is to "semantically conceptualize" example sentences by connecting FEs to knowledge base (KB) concepts. For example, connecting Employer FE to company concept in the KB enables the understanding that any (unseen) company can also be FE examples. However, a naive adoption of existing KB conceptualization technique, focusing on scenarios of conceptualizing a few terms, cannot 1) scale to many FE instances (average of 29.7 instances for all FEs) and 2) leverage interdependence between instances and concepts. We thus propose a scalable k-truss clustering and a Markov Random Field (MRF) model leveraging interdependence between conceptinstance, concept-concept, and instance-instance pairs. Our extensive analysis with real-life data validates that our approach improves not only the quality of the identified concepts for FrameNet, but also that of applications such as selectional preference.

Original languageEnglish
Title of host publication30th AAAI Conference on Artificial Intelligence, AAAI 2016
PublisherAAAI press
Pages2638-2644
Number of pages7
ISBN (Electronic)9781577357605
Publication statusPublished - 2016 Jan 1
Event30th AAAI Conference on Artificial Intelligence, AAAI 2016 - Phoenix, United States
Duration: 2016 Feb 122016 Feb 17

Publication series

Name30th AAAI Conference on Artificial Intelligence, AAAI 2016

Other

Other30th AAAI Conference on Artificial Intelligence, AAAI 2016
CountryUnited States
CityPhoenix
Period16/2/1216/2/17

Fingerprint

Semantics
Industry

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Park, J. W., Hwang, S., & Wang, H. (2016). Fine-grained semantic conceptualization of frameNet. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016 (pp. 2638-2644). (30th AAAI Conference on Artificial Intelligence, AAAI 2016). AAAI press.
Park, Jin Woo ; Hwang, Seungwon ; Wang, Haixun. / Fine-grained semantic conceptualization of frameNet. 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. pp. 2638-2644 (30th AAAI Conference on Artificial Intelligence, AAAI 2016).
@inproceedings{0fd9347f81e34aac9ac46a53ef1dd0a3,
title = "Fine-grained semantic conceptualization of frameNet",
abstract = "Understanding verbs is essential for many natural language tasks. To this end, large-scale lexical resources such as FrameNet have been manually constructed to annotate the semantics of verbs (frames) and their arguments (frame elements or FEs) in example sentences. Our goal is to {"}semantically conceptualize{"} example sentences by connecting FEs to knowledge base (KB) concepts. For example, connecting Employer FE to company concept in the KB enables the understanding that any (unseen) company can also be FE examples. However, a naive adoption of existing KB conceptualization technique, focusing on scenarios of conceptualizing a few terms, cannot 1) scale to many FE instances (average of 29.7 instances for all FEs) and 2) leverage interdependence between instances and concepts. We thus propose a scalable k-truss clustering and a Markov Random Field (MRF) model leveraging interdependence between conceptinstance, concept-concept, and instance-instance pairs. Our extensive analysis with real-life data validates that our approach improves not only the quality of the identified concepts for FrameNet, but also that of applications such as selectional preference.",
author = "Park, {Jin Woo} and Seungwon Hwang and Haixun Wang",
year = "2016",
month = "1",
day = "1",
language = "English",
series = "30th AAAI Conference on Artificial Intelligence, AAAI 2016",
publisher = "AAAI press",
pages = "2638--2644",
booktitle = "30th AAAI Conference on Artificial Intelligence, AAAI 2016",

}

Park, JW, Hwang, S & Wang, H 2016, Fine-grained semantic conceptualization of frameNet. in 30th AAAI Conference on Artificial Intelligence, AAAI 2016. 30th AAAI Conference on Artificial Intelligence, AAAI 2016, AAAI press, pp. 2638-2644, 30th AAAI Conference on Artificial Intelligence, AAAI 2016, Phoenix, United States, 16/2/12.

Fine-grained semantic conceptualization of frameNet. / Park, Jin Woo; Hwang, Seungwon; Wang, Haixun.

30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press, 2016. p. 2638-2644 (30th AAAI Conference on Artificial Intelligence, AAAI 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Fine-grained semantic conceptualization of frameNet

AU - Park, Jin Woo

AU - Hwang, Seungwon

AU - Wang, Haixun

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Understanding verbs is essential for many natural language tasks. To this end, large-scale lexical resources such as FrameNet have been manually constructed to annotate the semantics of verbs (frames) and their arguments (frame elements or FEs) in example sentences. Our goal is to "semantically conceptualize" example sentences by connecting FEs to knowledge base (KB) concepts. For example, connecting Employer FE to company concept in the KB enables the understanding that any (unseen) company can also be FE examples. However, a naive adoption of existing KB conceptualization technique, focusing on scenarios of conceptualizing a few terms, cannot 1) scale to many FE instances (average of 29.7 instances for all FEs) and 2) leverage interdependence between instances and concepts. We thus propose a scalable k-truss clustering and a Markov Random Field (MRF) model leveraging interdependence between conceptinstance, concept-concept, and instance-instance pairs. Our extensive analysis with real-life data validates that our approach improves not only the quality of the identified concepts for FrameNet, but also that of applications such as selectional preference.

AB - Understanding verbs is essential for many natural language tasks. To this end, large-scale lexical resources such as FrameNet have been manually constructed to annotate the semantics of verbs (frames) and their arguments (frame elements or FEs) in example sentences. Our goal is to "semantically conceptualize" example sentences by connecting FEs to knowledge base (KB) concepts. For example, connecting Employer FE to company concept in the KB enables the understanding that any (unseen) company can also be FE examples. However, a naive adoption of existing KB conceptualization technique, focusing on scenarios of conceptualizing a few terms, cannot 1) scale to many FE instances (average of 29.7 instances for all FEs) and 2) leverage interdependence between instances and concepts. We thus propose a scalable k-truss clustering and a Markov Random Field (MRF) model leveraging interdependence between conceptinstance, concept-concept, and instance-instance pairs. Our extensive analysis with real-life data validates that our approach improves not only the quality of the identified concepts for FrameNet, but also that of applications such as selectional preference.

UR - http://www.scopus.com/inward/record.url?scp=85007193530&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007193530&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85007193530

T3 - 30th AAAI Conference on Artificial Intelligence, AAAI 2016

SP - 2638

EP - 2644

BT - 30th AAAI Conference on Artificial Intelligence, AAAI 2016

PB - AAAI press

ER -

Park JW, Hwang S, Wang H. Fine-grained semantic conceptualization of frameNet. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016. AAAI press. 2016. p. 2638-2644. (30th AAAI Conference on Artificial Intelligence, AAAI 2016).