Definitional verbal patterns for semantic relation extraction

Sierra, Gerardo; Alarcón, Rodrigo; Aguilar, César; Bach, Carme

doi:10.1075/bct.23.04sie

Cited by 12 publications

(12 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Experts such as linguists, terminologists and translators took texts as point of departure to understand terms, extract them, capture lexical relations and build language resources, with different purposes. In this sense, corpus-based approaches have proved essential not only for the linguistic analysis of specialized languages (Bowker and Pearson 2002), but also for terminology extraction (Condamines 1995, Temmerman and Kerremans 2003, L'Homme 2004, definitional patterns extraction (Sierra et al 2008), taxonomy extraction (Nazar et al 2012), identifying conceptual relations (Condamines and Rebeyrolle 2001), ontology building (Jacquemin 2001;Malaisé et al 2005), enriching terminological databases (Schumann 2012), among many others.…”

Section: Approaches To Build a Glossarymentioning

confidence: 99%

Lights and shadows in creating a glossary about ontology engineering

Suárez-Figueroa¹,

de²,

Gómez-Pérez³

2013

TERM

View full text Add to dashboard Cite

This paper addresses the lack of an explicitly agreed and defined terminology in the ontology engineering field, and particularly, the need for a glossary, which consists of terms and definitions for actions when developing ontologies. The novelty of this paper lies in the precise description of a methodology for building a glossary with the processes and activities involved in ontology development as well as the relations between them (such as subtype, composition and synonym). The methodology proposed in this paper takes its inspiration from ideas taken from earlier research on methodological processes for creating multilingual terminological products and for defining a glossary in a particular domain as well as on domain knowledge organization. The description of our methodology includes the approach followed and the steps carried out, as well as the key issues that arise when the glossary was being created. So far as we are aware, this is the first attempt to normalize the terminology (denominations and definitions) of process and activities in ontology building.

show abstract

Section: Approaches To Build a Glossarymentioning

confidence: 99%

Lights and shadows in creating a glossary about ontology engineering

Suárez-Figueroa¹,

de²,

Gómez-Pérez³

2013

TERM

View full text Add to dashboard Cite

show abstract

“…For example, Malaise, Zweigenbaum and Bachimont (2004) used two corpora of different domains to develop and test their system, while Sierra et al (2008) used a vast corpus covering several domains, in order to test definitional patterns for Spanish. There are a few works of a more general nature, such as the one of Hearst (1992), that indicates some general patterns and proposes a heuristic to find new patterns for specific corpora.…”

Section: Definitions and Definition Extractionmentioning

confidence: 99%

Coping with highly imbalanced datasets: A case study with definition extraction in a multilingual setting

Gaudio¹,

Batista²,

Branco³

2013

Nat. Lang. Eng.

View full text Add to dashboard Cite

This paper addresses the task of automatic extraction of definitions by thoroughly exploring an approach that solely relies on machine learning techniques, and by focusing on the issue of the imbalance of relevant datasets. We obtained a breakthrough in terms of the automatic extraction of definitions, by extensively and systematically experimenting with different sampling techniques and their combination, as well as a range of different types of classifiers. Performance consistently scored in the range of 0.95-0.99 of area under the receiver operating characteristics, with a notorious improvement between 17 and 22 percentage points regarding the baseline of 0.73-0.77, for datasets with different rates of imbalance. Thus, the present paper also represents a contribution to the seminal work in natural language processing that points toward the importance of exploring the research path of applying sampling techniques to mitigate the bias induced by highly imbalanced datasets, and thus greatly improving the performance of a large range of tools that rely on them.

show abstract

“…Considering the instrumental relation, in Sierra et al (2008), for instance, the instrumental bears no relation to causality and is considered to be a mere functional definition (definiendum x is used by y), without further subtyping. Moreover, the formal aspect of the verbal instrumental predication maintains the nominal dominance of the definition per genus et differentia format (Sierra et al 2008: 81-83).…”

Section: Terminology: Towards Causal Meaning Dynamicsmentioning

confidence: 99%

Causal framing for medical instrumentality

Sambre¹,

Wermuth

2010

BJL

View full text Add to dashboard Cite

This paper explores the linguistic patterns of instrumentality in the titles of English medical research papers, at the interface between conceptual and linguistic structure, and offers a contribution to the little studied interrelationships between static and dynamic conceptual relations in medical ontology and LSP terminology. It is demonstrated how causal cues constitute the conceptual background against which instrumentals are profiled in the causal chain of the medical model. Taking inspiration from Talmy, frame semantics and construction grammar, the linguistic patterns in which causal and instrumental frame elements are co-activated are transcribed as complex patterns with partial morphological, syntactic and lexical marking of the conceptual relations under study. The paper offers an exploratory typology of causal cues for instrumentals and describes how multiple instruments can appear in medical LSP. The findings are relevant for those interested in the nexus between ontology, constructional aspects of expert language and frame semantics. Underspecification of dynamic instrumentality in medical ontology and terminologyThe dynamic aspect of instrumentality and the way it is embedded in causal thinking have been dealt with in both medical ontology (1.1) and terminology (1.2), albeit not with the required accuracy.

show abstract

Definitional verbal patterns for semantic relation extraction

Cited by 12 publications

References 3 publications

Lights and shadows in creating a glossary about ontology engineering

Lights and shadows in creating a glossary about ontology engineering

Coping with highly imbalanced datasets: A case study with definition extraction in a multilingual setting

Causal framing for medical instrumentality

Contact Info

Product

Resources

About