D 2012

Common Sense Inference using Verb Valency Frames

NEVĚŘILOVÁ, Zuzana and Marek GRÁC

Basic information

Original name

Common Sense Inference using Verb Valency Frames

Authors

NEVĚŘILOVÁ, Zuzana (203 Czech Republic, guarantor, belonging to the institution) and Marek GRÁC (703 Slovakia, belonging to the institution)

Edition

Berlin / Heidelberg, Proceedings of 15th International Conference on Text, Speech and Dialogue, p. 328-335, 8 pp. 2012

Publisher

Springer

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Czech Republic

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/12:00057557

Organization unit

Faculty of Informatics

ISBN

978-3-642-32789-6

ISSN

UT WoS

000337298700040

Keywords in English

common sense inference; common sense; implicit knowledge; verb valency; valency frame; valency lexicon

Tags

Tags

International impact, Reviewed
Změněno: 6/4/2015 22:19, Mgr. Vendula Hromádková

Abstract

V originále

In this paper we discuss common-sense reasoning from verb valency frames. While seeing verbs as predicates is not a new approach, processing inference as a transformation of valency frames is a promising method we developed with the help of large verb valency lexicons. We went through the whole process and evaluated it on several levels: parsing, valency assignment, syntactic transformation, syntactic and semantic evaluation of the generated propositions. We have chosen the domain of cooking recipes. We built a corpus with marked noun phrases, verb phrases and dependencies among them. We have manually created a basic set of inference rules and used it to infer new propositions from the corpus. Next, we extended this basic set and repeated the process. At first, we generated 1,738 sentences from 175 rules. 1,633 sentences were judged as (syntactically) correct and 1,533 were judged as (semantically) true. After extending the basic rule set we generated 2,826 propositions using 276 rules. 2,598 propositions were judged correct and 2,433 of the propositions were judged true.

Links

GAP401/10/0792, research and development project
Name: Temporální aspekty znalostí a informací
Investor: Czech Science Foundation
LM2010013, research and development project
Name: LINDAT-CLARIN: Institut pro analýzu, zpracování a distribuci lingvistických dat (Acronym: LINDAT-Clarin)
Investor: Ministry of Education, Youth and Sports of the CR