Representing semantics of texts - a non-statistical approach

Svetlana Hensman; John Dunnion

Representing semantics of texts - a non-statistical approach

Svetlana Hensman
, John Dunnion

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper describes a non-statistical approach for semantic annotation of documents by analysing their syntax and by using semantic/syntactic behaviour patterns described in VerbNet. We use a two-stage approach, firstly identifying the semantic roles in a sentence, and then using these roles to represent some of the relations between the concepts in the sentence and a list of noun behaviour patterns to resolve some of the unknown (generic) relations between concepts. All outlined algorithms were tested on two corpora which differs in size, type, style and genre, and the performance does not vary significantly.

Original language	English
Pages	209-214
Number of pages	6
Publication status	Published - 2005
Event	2nd International Joint Conference on Natural Language Processing Companion, IJCNLP 2005 - Jeju Island, Korea, Republic of Duration: 11 Oct 2005 → 13 Oct 2005

Conference

Conference	2nd International Joint Conference on Natural Language Processing Companion, IJCNLP 2005
Country/Territory	Korea, Republic of
City	Jeju Island
Period	11/10/05 → 13/10/05

Cite this

@conference{377227fb952d477096c54be626ba3e1d,

title = "Representing semantics of texts - a non-statistical approach",

abstract = "This paper describes a non-statistical approach for semantic annotation of documents by analysing their syntax and by using semantic/syntactic behaviour patterns described in VerbNet. We use a two-stage approach, firstly identifying the semantic roles in a sentence, and then using these roles to represent some of the relations between the concepts in the sentence and a list of noun behaviour patterns to resolve some of the unknown (generic) relations between concepts. All outlined algorithms were tested on two corpora which differs in size, type, style and genre, and the performance does not vary significantly.",

author = "Svetlana Hensman and John Dunnion",

note = "Publisher Copyright: {\textcopyright} 2005 Asian Federation of Natural Language Processing.; 2nd International Joint Conference on Natural Language Processing Companion, IJCNLP 2005 ; Conference date: 11-10-2005 Through 13-10-2005",

year = "2005",

language = "English",

pages = "209--214",

}

TY - CONF

T1 - Representing semantics of texts - a non-statistical approach

AU - Hensman, Svetlana

AU - Dunnion, John

PY - 2005

Y1 - 2005

N2 - This paper describes a non-statistical approach for semantic annotation of documents by analysing their syntax and by using semantic/syntactic behaviour patterns described in VerbNet. We use a two-stage approach, firstly identifying the semantic roles in a sentence, and then using these roles to represent some of the relations between the concepts in the sentence and a list of noun behaviour patterns to resolve some of the unknown (generic) relations between concepts. All outlined algorithms were tested on two corpora which differs in size, type, style and genre, and the performance does not vary significantly.

AB - This paper describes a non-statistical approach for semantic annotation of documents by analysing their syntax and by using semantic/syntactic behaviour patterns described in VerbNet. We use a two-stage approach, firstly identifying the semantic roles in a sentence, and then using these roles to represent some of the relations between the concepts in the sentence and a list of noun behaviour patterns to resolve some of the unknown (generic) relations between concepts. All outlined algorithms were tested on two corpora which differs in size, type, style and genre, and the performance does not vary significantly.

UR - https://www.scopus.com/pages/publications/105017716249

M3 - Paper

AN - SCOPUS:105017716249

SP - 209

EP - 214

T2 - 2nd International Joint Conference on Natural Language Processing Companion, IJCNLP 2005

Y2 - 11 October 2005 through 13 October 2005

ER -

Representing semantics of texts - a non-statistical approach

Abstract

Conference

Fingerprint

Cite this